Analyzing your idea with AI...

This commit is contained in:
ajaysi
2026-04-19 13:21:36 +05:30
parent e704aa7d87
commit 0732887c09
17 changed files with 6225 additions and 0 deletions

4
.gitignore vendored
View File

@@ -4,6 +4,10 @@ __pycache__/
*.db
*.sqlite*
nul
LICENSE
CHANGELOG.md
.trae/
.trae

14
README.md Normal file
View File

@@ -0,0 +1,14 @@
# Render CLI
## Installation
- [Homebrew](https://render.com/docs/cli#homebrew-macos-linux)
- [Direct Download](https://render.com/docs/cli#direct-download)
## Documentation
Documentation is hosted at https://render.com/docs/cli.
## Contributing
To create a new command, use the `cmd/template.go` template file as a starting point. Reference the [CLI Style Guide](docs/STYLE.md) to learn more about command naming, flags, arguments, and help text conventions.

672
_session_backup/App.tsx Normal file
View File

@@ -0,0 +1,672 @@
import React from 'react';
import { BrowserRouter as Router, Routes, Route, Navigate, useLocation } from 'react-router-dom';
import { Box, CircularProgress, Typography } from '@mui/material';
import { CopilotKit } from "@copilotkit/react-core";
import { ClerkProvider, useAuth } from '@clerk/clerk-react';
import "@copilotkit/react-ui/styles.css";
import Wizard from './components/OnboardingWizard/Wizard';
import MainDashboard from './components/MainDashboard/MainDashboard';
import SEODashboard from './components/SEODashboard/SEODashboard';
import ContentPlanningDashboard from './components/ContentPlanningDashboard/ContentPlanningDashboard';
import FacebookWriter from './components/FacebookWriter/FacebookWriter';
import LinkedInWriter from './components/LinkedInWriter/LinkedInWriter';
import BlogWriter from './components/BlogWriter/BlogWriter';
import StoryWriter from './components/StoryWriter/StoryWriter';
import { StoryProjectList } from './components/StoryWriter/StoryProjectList';
import YouTubeCreator from './components/YouTubeCreator/YouTubeCreator';
import { CreateStudio, EditStudio, UpscaleStudio, ControlStudio, SocialOptimizer, AssetLibrary, ImageStudioDashboard, FaceSwapStudio, CompressionStudio, ImageProcessingStudio } from './components/ImageStudio';
import {
VideoStudioDashboard,
CreateVideo,
AvatarVideo,
EnhanceVideo,
ExtendVideo,
EditVideo,
TransformVideo,
SocialVideo,
FaceSwap,
VideoTranslate,
VideoBackgroundRemover,
AddAudioToVideo,
LibraryVideo,
} from './components/VideoStudio';
import {
ProductMarketingDashboard,
ProductPhotoshootStudio,
ProductAnimationStudio,
ProductVideoStudio,
ProductAvatarStudio,
} from './components/ProductMarketing';
import PodcastDashboard from './components/PodcastMaker/PodcastDashboard';
import PricingPage from './components/Pricing/PricingPage';
import WixTestPage from './components/WixTestPage/WixTestPage';
import WixCallbackPage from './components/WixCallbackPage/WixCallbackPage';
import WordPressCallbackPage from './components/WordPressCallbackPage/WordPressCallbackPage';
import BingCallbackPage from './components/BingCallbackPage/BingCallbackPage';
import BingAnalyticsStorage from './components/BingAnalyticsStorage/BingAnalyticsStorage';
import ResearchDashboard from './pages/ResearchDashboard';
import IntentResearchTest from './pages/IntentResearchTest';
import SchedulerDashboard from './pages/SchedulerDashboard';
import BillingPage from './pages/BillingPage';
import ApprovalsPage from './pages/ApprovalsPage';
import TeamActivityPage from './pages/TeamActivityPage';
import StripeDisputesDashboard from './pages/StripeDisputesDashboard';
import ProtectedRoute from './components/shared/ProtectedRoute';
import GSCAuthCallback from './components/SEODashboard/components/GSCAuthCallback';
import Landing from './components/Landing/Landing';
import ErrorBoundary from './components/shared/ErrorBoundary';
import ErrorBoundaryTest from './components/shared/ErrorBoundaryTest';
import CopilotKitDegradedBanner from './components/shared/CopilotKitDegradedBanner';
import { OnboardingProvider } from './contexts/OnboardingContext';
import { SubscriptionProvider, useSubscription } from './contexts/SubscriptionContext';
import { CopilotKitHealthProvider } from './contexts/CopilotKitHealthContext';
import { useOAuthTokenAlerts } from './hooks/useOAuthTokenAlerts';
import { setAuthTokenGetter, setClerkSignOut } from './api/client';
import { setMediaAuthTokenGetter } from './utils/fetchMediaBlobUrl';
import { setBillingAuthTokenGetter } from './services/billingService';
import { useOnboarding } from './contexts/OnboardingContext';
import { useState, useEffect } from 'react';
import ConnectionErrorPage from './components/shared/ConnectionErrorPage';
import { isPodcastOnlyDemoMode } from './utils/demoMode';
// interface OnboardingStatus {
// onboarding_required: boolean;
// onboarding_complete: boolean;
// current_step?: number;
// total_steps?: number;
// completion_percentage?: number;
// }
// Conditional CopilotKit wrapper that only shows sidebar on content-planning route
const ConditionalCopilotKit: React.FC<{ children: React.ReactNode }> = ({ children }) => {
// Do not render CopilotSidebar here. Let specific pages/components control it.
return <>{children}</>;
};
// Wrapper to only enable CopilotKit checks/provider when user is authenticated
// This prevents CopilotKit from running on the Landing page
const AuthenticatedCopilotWrapper: React.FC<{
children: React.ReactNode;
apiKey: string;
}> = ({ children, apiKey }) => {
const { isSignedIn } = useAuth();
const location = useLocation();
// Exclude CopilotKit from running on:
// 1. Landing page (handled by !isSignedIn)
// 2. Onboarding pages (to prevent health check timeouts)
// 3. Podcast-only demo mode (CopilotKit not needed)
const isPodcastOnly = isPodcastOnlyDemoMode();
const shouldExcludeCopilot = !isSignedIn || location.pathname.startsWith('/onboarding') || isPodcastOnly;
if (shouldExcludeCopilot) {
return <>{children}</>;
}
const hasKey = apiKey && apiKey.trim();
if (hasKey) {
// Enhanced error handler that updates health context
const handleCopilotKitError = (e: any) => {
console.error("CopilotKit Error:", e);
// Try to get health context if available
// We'll use a custom event to notify health context since we can't access it directly here
const errorMessage = e?.error?.message || e?.message || 'CopilotKit error occurred';
const errorType = errorMessage.toLowerCase();
// Differentiate between fatal and transient errors
const isFatalError =
errorType.includes('cors') ||
errorType.includes('ssl') ||
errorType.includes('certificate') ||
errorType.includes('403') ||
errorType.includes('forbidden') ||
errorType.includes('ERR_CERT_COMMON_NAME_INVALID');
// Dispatch event for health context to listen to
window.dispatchEvent(new CustomEvent('copilotkit-error', {
detail: {
error: e,
errorMessage,
isFatal: isFatalError,
}
}));
};
return (
<CopilotKitHealthProvider initialHealthStatus={true}>
<CopilotKitDegradedBanner />
<ErrorBoundary
context="CopilotKit"
showDetails={process.env.NODE_ENV === 'development'}
fallback={
<Box sx={{ p: 3, textAlign: 'center' }}>
<Typography variant="h6" color="warning" gutterBottom>
Chat Unavailable
</Typography>
<Typography variant="body2" color="textSecondary">
CopilotKit encountered an error. The app continues to work with manual controls.
</Typography>
</Box>
}
>
<CopilotKit
publicApiKey={apiKey}
showDevConsole={false}
onError={handleCopilotKitError}
>
{children}
</CopilotKit>
</ErrorBoundary>
</CopilotKitHealthProvider>
);
}
return (
<CopilotKitHealthProvider initialHealthStatus={false}>
<CopilotKitDegradedBanner />
{children}
</CopilotKitHealthProvider>
);
};
// Component to handle initial routing based on subscription and onboarding status
// Flow: Subscription → Onboarding → Dashboard
const InitialRouteHandler: React.FC = () => {
const { loading, error, isOnboardingComplete, initializeOnboarding, data } = useOnboarding();
const { subscription, loading: subscriptionLoading, checkSubscription } = useSubscription();
const [connectionError, setConnectionError] = useState<{
hasError: boolean;
error: Error | null;
}>({
hasError: false,
error: null,
});
// Poll for OAuth token alerts and show toast notifications
// Only enabled when user is authenticated (has subscription)
useOAuthTokenAlerts({
enabled: subscription?.active === true,
interval: 60000, // Poll every 1 minute
});
// Check subscription on mount (non-blocking - don't wait for it to route)
useEffect(() => {
// Delay subscription check slightly to allow auth token getter to be installed first
const timeoutId = setTimeout(async () => {
// Retry logic for initial subscription check
const maxRetries = 3;
for (let attempt = 0; attempt < maxRetries; attempt++) {
try {
await checkSubscription();
break; // Success
} catch (err) {
console.error(`App: Subscription check attempt ${attempt + 1} failed:`, err);
// If it's a connection error and we have retries left, wait and retry
const isConnectionError = err instanceof Error && (err.name === 'NetworkError' || err.name === 'ConnectionError');
if (isConnectionError && attempt < maxRetries - 1) {
const delay = 1000 * Math.pow(2, attempt); // 1s, 2s
await new Promise(resolve => setTimeout(resolve, delay));
continue;
}
// If final attempt or not a connection error, handle it
if (attempt === maxRetries - 1 || !isConnectionError) {
if (isConnectionError) {
setConnectionError({
hasError: true,
error: err as Error,
});
}
// Don't block routing on other errors
}
}
}
}, 100); // Small delay to ensure TokenInstaller has run
return () => clearTimeout(timeoutId);
}, []); // Remove checkSubscription dependency to prevent loop
// Initialize onboarding only after subscription is confirmed
useEffect(() => {
if (subscription && !subscriptionLoading) {
// Check if user is new (no subscription record at all)
const isNewUser = !subscription || subscription.plan === 'none';
console.log('InitialRouteHandler: Subscription data received:', {
plan: subscription.plan,
active: subscription.active,
isNewUser,
subscriptionLoading
});
if (subscription.active && !isNewUser) {
console.log('InitialRouteHandler: Subscription confirmed, initializing onboarding...');
initializeOnboarding();
}
}
}, [subscription, subscriptionLoading, initializeOnboarding]);
// Handle connection error - show connection error page
if (connectionError.hasError) {
const handleRetry = () => {
setConnectionError({
hasError: false,
error: null,
});
// Re-trigger the subscription check using context
checkSubscription().catch((err) => {
if (err instanceof Error && (err.name === 'NetworkError' || err.name === 'ConnectionError')) {
setConnectionError({
hasError: true,
error: err,
});
}
});
};
const handleGoHome = () => {
window.location.href = '/';
};
return (
<ConnectionErrorPage
onRetry={handleRetry}
onGoHome={handleGoHome}
message={connectionError.error?.message || "Backend service is not available. Please check if the server is running."}
title="Connection Error"
/>
);
}
// Loading state - only wait for onboarding init, not subscription check
// Subscription check is non-blocking and happens in background
const waitingForOnboardingInit = loading || !data;
if (loading || waitingForOnboardingInit) {
return (
<Box
display="flex"
flexDirection="column"
alignItems="center"
justifyContent="center"
minHeight="100vh"
gap={2}
>
<CircularProgress size={60} />
<Typography variant="h6" color="textSecondary">
{subscriptionLoading ? 'Checking subscription...' : 'Preparing your workspace...'}
</Typography>
</Box>
);
}
// Error state
if (error) {
return (
<Box
display="flex"
flexDirection="column"
alignItems="center"
justifyContent="center"
minHeight="100vh"
gap={2}
p={3}
>
<Typography variant="h5" color="error" gutterBottom>
Error
</Typography>
<Typography variant="body1" color="textSecondary" textAlign="center">
{error}
</Typography>
</Box>
);
}
// Decision tree for SIGNED-IN users:
// Priority: Subscription → Onboarding → Dashboard (as per user flow: Landing → Subscription → Onboarding → Dashboard)
// 1. If subscription is still loading, show loading state
if (subscriptionLoading) {
return (
<Box
display="flex"
flexDirection="column"
alignItems="center"
justifyContent="center"
minHeight="100vh"
gap={2}
>
<CircularProgress size={60} />
<Typography variant="h6" color="textSecondary">
Checking subscription...
</Typography>
</Box>
);
}
// 2. No subscription data yet - handle gracefully
// If onboarding is complete, allow access to dashboard (user already went through flow)
// If onboarding not complete, check if subscription check is still loading or failed
if (!subscription) {
if (isOnboardingComplete) {
console.log('InitialRouteHandler: Onboarding complete but no subscription data → Dashboard (allow access)');
return <Navigate to="/dashboard" replace />;
}
// Onboarding not complete and no subscription data
// If subscription check is still loading, show loading state
if (subscriptionLoading) {
return (
<Box
display="flex"
flexDirection="column"
alignItems="center"
justifyContent="center"
minHeight="100vh"
gap={2}
>
<CircularProgress size={60} />
<Typography variant="h6" color="textSecondary">
Checking subscription...
</Typography>
</Box>
);
}
// Subscription check completed but returned null/undefined
// This likely means no subscription - redirect to pricing
console.log('InitialRouteHandler: No subscription data after check → Pricing page');
return <Navigate to="/pricing" replace />;
}
// 3. Check subscription status first
const isNewUser = !subscription || subscription.plan === 'none';
// No active subscription → Show modal (SubscriptionContext handles this)
// Don't redirect immediately - let the modal show first
// User can click "Renew Subscription" button in modal to go to pricing
// Or click "Maybe Later" to dismiss (but they still can't use features)
if (isNewUser || !subscription.active) {
console.log('InitialRouteHandler: No active subscription - modal will be shown by SubscriptionContext');
// Note: SubscriptionContext will show the modal automatically when subscription is inactive
// We still redirect to pricing for new users, but allow existing users with expired subscriptions
// to see the modal first. The modal has a "Renew Subscription" button that navigates to pricing.
// For new users (no subscription at all), redirect to pricing immediately
if (isNewUser) {
console.log('InitialRouteHandler: New user (no subscription) → Pricing page');
return <Navigate to="/pricing" replace />;
}
// For existing users with inactive subscription, show modal but don't redirect immediately
// The modal will be shown by SubscriptionContext, and user can click "Renew Subscription"
// Allow access to dashboard (modal will be shown and block functionality)
console.log('InitialRouteHandler: Inactive subscription - allowing access to show modal');
// Continue to onboarding/dashboard flow - modal will be shown by SubscriptionContext
}
// 4. Has active subscription, check onboarding status
if (!isOnboardingComplete) {
console.log('InitialRouteHandler: Subscription active but onboarding incomplete → Onboarding');
return <Navigate to="/onboarding" replace />;
}
// 5. Has subscription AND completed onboarding → Dashboard
console.log('InitialRouteHandler: All set (subscription + onboarding) → Dashboard');
return <Navigate to="/dashboard" replace />;
};
// Root route that chooses Landing (signed out) or InitialRouteHandler (signed in)
const RootRoute: React.FC = () => {
const { isSignedIn } = useAuth();
if (isSignedIn) {
return <InitialRouteHandler />;
}
return <Landing />;
};
// Installs Clerk auth token getter into axios clients and stores user_id
// Must render under ClerkProvider
const TokenInstaller: React.FC = () => {
const { getToken, userId, isSignedIn, signOut } = useAuth();
// Store user_id in localStorage when user signs in
useEffect(() => {
if (isSignedIn && userId) {
console.log('TokenInstaller: Storing user_id in localStorage:', userId);
localStorage.setItem('user_id', userId);
// Trigger event to notify SubscriptionContext that user is authenticated
window.dispatchEvent(new CustomEvent('user-authenticated', { detail: { userId } }));
} else if (!isSignedIn) {
// Clear user_id when signed out
console.log('TokenInstaller: Clearing user_id from localStorage');
localStorage.removeItem('user_id');
}
}, [isSignedIn, userId]);
// Install token getter for API calls
useEffect(() => {
const tokenGetter = async () => {
try {
const template = process.env.REACT_APP_CLERK_JWT_TEMPLATE;
// If a template is provided and it's not a placeholder, request a template-specific JWT
if (template && template !== 'your_jwt_template_name_here') {
// @ts-ignore Clerk types allow options object
return await getToken({ template });
}
return await getToken();
} catch {
return null;
}
};
// Set token getter for main API client
setAuthTokenGetter(tokenGetter);
// Set token getter for billing API client (same function)
setBillingAuthTokenGetter(tokenGetter);
// Set token getter for media blob URL fetcher (for authenticated image/video requests)
setMediaAuthTokenGetter(tokenGetter);
}, [getToken]);
// Install Clerk signOut function for handling expired tokens
useEffect(() => {
if (signOut) {
setClerkSignOut(async () => {
await signOut();
});
}
}, [signOut]);
return null;
};
const App: React.FC = () => {
// React Hooks MUST be at the top before any conditionals
const [loading, setLoading] = useState(true);
// Get CopilotKit key from localStorage or .env
const [copilotApiKey, setCopilotApiKey] = useState(() => {
const savedKey = localStorage.getItem('copilotkit_api_key');
const envKey = process.env.REACT_APP_COPILOTKIT_API_KEY || '';
const key = (savedKey || envKey).trim();
// Validate key format if present
if (key && !key.startsWith('ck_pub_')) {
console.warn('CopilotKit API key format invalid - must start with ck_pub_');
}
return key;
});
// Initialize app - loading state will be managed by InitialRouteHandler
useEffect(() => {
// Remove manual health check - connection errors are handled by ErrorBoundary
setLoading(false);
}, []);
// Listen for CopilotKit key updates
useEffect(() => {
const handleKeyUpdate = (event: CustomEvent) => {
const newKey = event.detail?.apiKey;
if (newKey) {
console.log('App: CopilotKit key updated, reloading...');
setCopilotApiKey(newKey);
setTimeout(() => window.location.reload(), 500);
}
};
window.addEventListener('copilotkit-key-updated', handleKeyUpdate as EventListener);
return () => window.removeEventListener('copilotkit-key-updated', handleKeyUpdate as EventListener);
}, []);
// Token installer must be inside ClerkProvider; see TokenInstaller below
if (loading) {
return (
<Box
display="flex"
flexDirection="column"
alignItems="center"
justifyContent="center"
minHeight="100vh"
gap={2}
>
<CircularProgress size={60} />
<Typography variant="h6" color="textSecondary">
Connecting to ALwrity...
</Typography>
</Box>
);
}
// Get environment variables with fallbacks
const clerkPublishableKey = process.env.REACT_APP_CLERK_PUBLISHABLE_KEY || '';
const clerkJSUrl = process.env.REACT_APP_CLERK_JS_URL;
// Show error if required keys are missing
if (!clerkPublishableKey) {
return (
<Box sx={{ p: 3, textAlign: 'center' }}>
<Typography color="error" variant="h6">
Missing Clerk Publishable Key
</Typography>
<Typography variant="body2" sx={{ mt: 1 }}>
Please add REACT_APP_CLERK_PUBLISHABLE_KEY to your .env file
</Typography>
</Box>
);
}
// Render app with or without CopilotKit based on whether we have a key
const renderApp = () => {
return (
<Router>
<AuthenticatedCopilotWrapper apiKey={copilotApiKey}>
<ConditionalCopilotKit>
<TokenInstaller />
<Routes>
<Route path="/" element={<RootRoute />} />
<Route
path="/onboarding"
element={
<ErrorBoundary context="Onboarding Wizard" showDetails>
<Wizard />
</ErrorBoundary>
}
/>
{/* Error Boundary Testing - Development Only */}
{process.env.NODE_ENV === 'development' && (
<Route path="/error-test" element={<ErrorBoundaryTest />} />
)}
<Route path="/dashboard" element={<ProtectedRoute><MainDashboard /></ProtectedRoute>} />
<Route path="/seo" element={<ProtectedRoute><SEODashboard /></ProtectedRoute>} />
<Route path="/seo-dashboard" element={<ProtectedRoute><SEODashboard /></ProtectedRoute>} />
<Route path="/content-planning" element={<ProtectedRoute><ContentPlanningDashboard /></ProtectedRoute>} />
<Route path="/facebook-writer" element={<ProtectedRoute><FacebookWriter /></ProtectedRoute>} />
<Route path="/linkedin-writer" element={<ProtectedRoute><LinkedInWriter /></ProtectedRoute>} />
<Route path="/blog-writer" element={<ProtectedRoute><BlogWriter /></ProtectedRoute>} />
<Route path="/story-writer" element={<ProtectedRoute><StoryWriter /></ProtectedRoute>} />
<Route path="/story-projects" element={<ProtectedRoute><StoryProjectList /></ProtectedRoute>} />
<Route path="/youtube-creator" element={<ProtectedRoute><YouTubeCreator /></ProtectedRoute>} />
<Route path="/podcast-maker" element={<ProtectedRoute><PodcastDashboard /></ProtectedRoute>} />
<Route path="/image-studio" element={<ProtectedRoute><ImageStudioDashboard /></ProtectedRoute>} />
<Route path="/video-studio" element={<ProtectedRoute><VideoStudioDashboard /></ProtectedRoute>} />
<Route path="/video-studio/create" element={<ProtectedRoute><CreateVideo /></ProtectedRoute>} />
<Route path="/video-studio/avatar" element={<ProtectedRoute><AvatarVideo /></ProtectedRoute>} />
<Route path="/video-studio/enhance" element={<ProtectedRoute><EnhanceVideo /></ProtectedRoute>} />
<Route path="/video-studio/extend" element={<ProtectedRoute><ExtendVideo /></ProtectedRoute>} />
<Route path="/video-studio/edit" element={<ProtectedRoute><EditVideo /></ProtectedRoute>} />
<Route path="/video-studio/transform" element={<ProtectedRoute><TransformVideo /></ProtectedRoute>} />
<Route path="/video-studio/social" element={<ProtectedRoute><SocialVideo /></ProtectedRoute>} />
<Route path="/video-studio/face-swap" element={<ProtectedRoute><FaceSwap /></ProtectedRoute>} />
<Route path="/video-studio/video-translate" element={<ProtectedRoute><VideoTranslate /></ProtectedRoute>} />
<Route path="/video-studio/video-background-remover" element={<ProtectedRoute><VideoBackgroundRemover /></ProtectedRoute>} />
<Route path="/video-studio/add-audio-to-video" element={<ProtectedRoute><AddAudioToVideo /></ProtectedRoute>} />
<Route path="/video-studio/library" element={<ProtectedRoute><LibraryVideo /></ProtectedRoute>} />
<Route path="/image-generator" element={<ProtectedRoute><CreateStudio /></ProtectedRoute>} />
<Route path="/image-editor" element={<ProtectedRoute><EditStudio /></ProtectedRoute>} />
<Route path="/image-upscale" element={<ProtectedRoute><UpscaleStudio /></ProtectedRoute>} />
<Route path="/image-control" element={<ProtectedRoute><ControlStudio /></ProtectedRoute>} />
<Route path="/image-studio/face-swap" element={<ProtectedRoute><FaceSwapStudio /></ProtectedRoute>} />
<Route path="/image-studio/compress" element={<ProtectedRoute><CompressionStudio /></ProtectedRoute>} />
<Route path="/image-studio/processing" element={<ProtectedRoute><ImageProcessingStudio /></ProtectedRoute>} />
<Route path="/image-studio/social-optimizer" element={<ProtectedRoute><SocialOptimizer /></ProtectedRoute>} />
<Route path="/asset-library" element={<ProtectedRoute><AssetLibrary /></ProtectedRoute>} />
<Route path="/campaign-creator" element={<ProtectedRoute><ProductMarketingDashboard /></ProtectedRoute>} />
<Route path="/campaign-creator/photoshoot" element={<ProtectedRoute><ProductPhotoshootStudio /></ProtectedRoute>} />
<Route path="/campaign-creator/animation" element={<ProtectedRoute><ProductAnimationStudio /></ProtectedRoute>} />
<Route path="/campaign-creator/video" element={<ProtectedRoute><ProductVideoStudio /></ProtectedRoute>} />
<Route path="/campaign-creator/avatar" element={<ProtectedRoute><ProductAvatarStudio /></ProtectedRoute>} />
<Route path="/product-marketing" element={<Navigate to="/campaign-creator" replace />} />
<Route path="/scheduler-dashboard" element={<ProtectedRoute><SchedulerDashboard /></ProtectedRoute>} />
<Route path="/billing" element={<ProtectedRoute><BillingPage /></ProtectedRoute>} />
<Route path="/approvals" element={<ProtectedRoute><ApprovalsPage /></ProtectedRoute>} />
<Route path="/team-activity" element={<ProtectedRoute><TeamActivityPage /></ProtectedRoute>} />
<Route path="/stripe-disputes" element={<ProtectedRoute><StripeDisputesDashboard /></ProtectedRoute>} />
<Route path="/pricing" element={<PricingPage />} />
<Route path="/research-test" element={<ResearchDashboard />} />
<Route path="/research-dashboard" element={<ResearchDashboard />} />
<Route path="/alwrity-researcher" element={<ResearchDashboard />} />
<Route path="/intent-research" element={<IntentResearchTest />} />
<Route path="/wix-test" element={<WixTestPage />} />
<Route path="/wix-test-direct" element={<WixTestPage />} />
<Route path="/wix/callback" element={<WixCallbackPage />} />
<Route path="/wp/callback" element={<WordPressCallbackPage />} />
<Route path="/gsc/callback" element={<GSCAuthCallback />} />
<Route path="/bing/callback" element={<BingCallbackPage />} />
<Route path="/bing-analytics-storage" element={<ProtectedRoute><BingAnalyticsStorage /></ProtectedRoute>} />
</Routes>
</ConditionalCopilotKit>
</AuthenticatedCopilotWrapper>
</Router>
);
};
return (
<ErrorBoundary
context="Application Root"
showDetails={process.env.NODE_ENV === 'development'}
onError={(error, errorInfo) => {
// Custom error handler - send to analytics/monitoring
console.error('Global error caught:', { error, errorInfo });
// TODO: Send to error tracking service (Sentry, LogRocket, etc.)
}}
>
<ClerkProvider publishableKey={clerkPublishableKey} clerkJSUrl={clerkJSUrl}>
<SubscriptionProvider>
<OnboardingProvider>
{renderApp()}
</OnboardingProvider>
</SubscriptionProvider>
</ClerkProvider>
</ErrorBoundary>
);
};
export default App;

View File

@@ -0,0 +1,537 @@
import React, { useMemo, useCallback } from "react";
import { Stack, Typography, Chip, Divider, Box, alpha, Paper, Tooltip } from "@mui/material";
import {
Insights as InsightsIcon,
Search as SearchIcon,
AttachMoney as AttachMoneyIcon,
EditNote as EditNoteIcon,
Article as ArticleIcon,
AutoAwesome as AutoAwesomeIcon,
FormatQuote as FormatQuoteIcon,
Campaign as CampaignIcon,
Explore as ExploreIcon,
} from "@mui/icons-material";
import { Research, ResearchInsight } from "../types";
import { GlassyCard, glassyCardSx, PrimaryButton } from "../ui";
import { FactCard } from "../FactCard";
interface ResearchSummaryProps {
research: Research;
canGenerateScript: boolean;
onGenerateScript: () => void;
}
export const ResearchSummary: React.FC<ResearchSummaryProps> = ({
research,
canGenerateScript,
onGenerateScript,
}) => {
// Simple markdown-to-HTML converter
const renderMarkdown = useCallback((text: string) => {
if (!text) return null;
return text
.split('\n')
.filter(line => line.trim() !== '') // Remove empty lines
.map((line, i) => {
// Handle bold
let processedLine = line.replace(/\*\*(.*?)\*\*/g, '<strong>$1</strong>');
// Handle lists
if (processedLine.trim().startsWith('- ') || processedLine.trim().startsWith('* ')) {
return <li key={i} dangerouslySetInnerHTML={{ __html: processedLine.trim().substring(2) }} style={{ marginBottom: '4px', fontSize: '0.9rem' }} />;
}
// Handle headers - make them smaller
if (processedLine.startsWith('### ')) {
return <Typography key={i} variant="subtitle2" fontWeight={700} sx={{ mt: 1.5, mb: 0.5, color: '#1e293b' }}>{processedLine.substring(4)}</Typography>;
}
if (processedLine.startsWith('## ')) {
return <Typography key={i} variant="subtitle1" fontWeight={700} sx={{ mt: 1.5, mb: 0.5, color: '#0f172a' }}>{processedLine.substring(3)}</Typography>;
}
// Paragraphs - compact spacing
return processedLine.trim() ? <p key={i} dangerouslySetInnerHTML={{ __html: processedLine }} style={{ margin: '4px 0', fontSize: '0.9rem' }} /> : null;
});
}, []);
return (
<GlassyCard sx={glassyCardSx}>
<Stack spacing={3}>
<Stack direction="row" justifyContent="space-between" alignItems="center" flexWrap="wrap" gap={2}>
<Stack direction="row" alignItems="center" spacing={2} sx={{ flex: 1 }}>
<Typography variant="h6" sx={{ display: "flex", alignItems: "center", gap: 1, color: "#0f172a", fontWeight: 700 }}>
<InsightsIcon />
Research Summary
</Typography>
{/* Research Metadata - Moved alongside title */}
<Stack direction="row" spacing={1.5} flexWrap="wrap">
{research.searchQueries && research.searchQueries.length > 0 && (
<Chip
icon={<SearchIcon sx={{ fontSize: "1rem !important" }} />}
label={`${research.searchQueries.length} search${research.searchQueries.length > 1 ? "es" : ""}`}
size="small"
sx={{
background: alpha("#667eea", 0.1),
color: "#667eea",
fontWeight: 600,
border: "1px solid rgba(102, 126, 234, 0.2)",
}}
/>
)}
{research.searchType && (
<Chip
label={`${research.searchType.charAt(0).toUpperCase() + research.searchType.slice(1)} search`}
size="small"
sx={{
background: alpha("#10b981", 0.1),
color: "#059669",
fontWeight: 600,
border: "1px solid rgba(16, 185, 129, 0.2)",
}}
/>
)}
{research.sourceCount !== undefined && (
<Chip
label={`${research.sourceCount} source${research.sourceCount !== 1 ? "s" : ""}`}
size="small"
sx={{
background: alpha("#6366f1", 0.1),
color: "#4f46e5",
fontWeight: 600,
border: "1px solid rgba(99, 102, 241, 0.2)",
}}
/>
)}
{research.cost !== undefined && (
<Chip
icon={<AttachMoneyIcon sx={{ fontSize: "0.875rem !important" }} />}
label={`$${research.cost.toFixed(3)}`}
size="small"
sx={{
background: alpha("#f59e0b", 0.1),
color: "#d97706",
fontWeight: 600,
border: "1px solid rgba(245, 158, 11, 0.2)",
}}
/>
)}
</Stack>
</Stack>
<PrimaryButton
onClick={onGenerateScript}
disabled={!canGenerateScript}
startIcon={<EditNoteIcon />}
tooltip={!canGenerateScript ? "Complete research to generate script" : "Generate AI-powered script from research"}
>
Generate Script
</PrimaryButton>
</Stack>
<Box sx={{ width: "100%" }}>
{/* Main Summary */}
{research.summary && (
<Paper
elevation={0}
sx={{
p: 2.5,
mb: 3,
background: "#f8fafc",
border: "1px solid rgba(0,0,0,0.06)",
borderRadius: 2,
}}
>
<Typography variant="subtitle2" sx={{ mb: 1.5, color: "#64748b", fontWeight: 700, fontSize: "0.75rem", textTransform: "uppercase", letterSpacing: "0.05em", display: "flex", alignItems: "center", gap: 1 }}>
<AutoAwesomeIcon fontSize="small" sx={{ color: "#667eea", fontSize: "1rem" }} />
Executive Summary
</Typography>
<Box sx={{
lineHeight: 1.6,
fontSize: "0.9rem",
color: "#334155",
"& p": { m: 0, mb: 1 },
"& ul": { m: 0, mb: 1, pl: 2.5 },
"& li": { mb: 0.5 },
"& strong": { color: "#0f172a", fontWeight: 600 }
}}>
{renderMarkdown(research.summary)}
</Box>
</Paper>
)}
{/* Deep Insights */}
{(research.keyInsights && research.keyInsights.length > 0) ? (
<Box sx={{ mb: 4 }}>
<Typography variant="h6" sx={{ mb: 2, color: "#0f172a", fontWeight: 700, display: "flex", alignItems: "center", gap: 1 }}>
<ArticleIcon sx={{ color: "#667eea" }} />
Deep Insights
</Typography>
<Stack spacing={2.5}>
{research.keyInsights.map((insight: ResearchInsight, idx: number) => (
<Paper
key={idx}
elevation={0}
sx={{
p: 2.5,
background: "#ffffff",
border: "1px solid rgba(0,0,0,0.06)",
boxShadow: "0 2px 12px rgba(0,0,0,0.03)",
borderRadius: 2,
}}
>
<Stack direction="row" justifyContent="space-between" alignItems="flex-start" sx={{ mb: 1.5 }}>
<Typography variant="subtitle1" sx={{ color: "#0f172a", fontWeight: 700 }}>
{insight.title}
</Typography>
{insight.source_indices && insight.source_indices.length > 0 && (
<Stack direction="row" spacing={0.5}>
{insight.source_indices.map(sIdx => {
const sourceIdx = sIdx - 1;
const fact = research.factCards[sourceIdx];
const sourceUrl = fact?.url;
const hasUrl = !!sourceUrl;
const hue = (sIdx * 47 + 220) % 360;
const gradientFrom = `hsl(${hue}, 70%, 55%)`;
const gradientTo = `hsl(${(hue + 30) % 360}, 80%, 65%)`;
return (
<Tooltip
key={sIdx}
title={hasUrl ? (
<Box sx={{ maxWidth: 300, wordBreak: "break-all" }}>
<Typography variant="caption" sx={{ color: "#fff", fontWeight: 600 }}>Source {sIdx}</Typography>
<br />
<Typography variant="caption" sx={{ color: "rgba(255,255,255,0.8)", fontSize: "0.65rem" }}>{sourceUrl}</Typography>
</Box>
) : `Source ${sIdx}`}
arrow
placement="top"
>
<Chip
label={hasUrl ? `S${sIdx}` : `S${sIdx}`}
size="small"
onClick={hasUrl ? () => window.open(sourceUrl, "_blank", "noopener,noreferrer") : undefined}
sx={{
height: 24,
minWidth: 36,
fontSize: '0.7rem',
fontWeight: 800,
fontFamily: "'Inter', 'Roboto', monospace",
letterSpacing: "0.02em",
border: "none",
background: hasUrl
? `linear-gradient(135deg, ${gradientFrom}, ${gradientTo})`
: `linear-gradient(135deg, ${alpha(gradientFrom, 0.3)}, ${alpha(gradientTo, 0.3)})`,
color: hasUrl ? "#fff" : alpha("#fff", 0.7),
cursor: hasUrl ? "pointer" : "default",
borderRadius: "8px",
px: 0.5,
boxShadow: hasUrl
? `0 2px 8px ${alpha(gradientFrom, 0.35)}, inset 0 1px 0 ${alpha("#fff", 0.2)}`
: "none",
transition: "all 0.2s ease",
"&:hover": hasUrl ? {
background: `linear-gradient(135deg, ${gradientTo}, ${gradientFrom})`,
boxShadow: `0 4px 14px ${alpha(gradientFrom, 0.5)}, inset 0 1px 0 ${alpha("#fff", 0.3)}`,
transform: "translateY(-1px)",
} : {},
}}
/>
</Tooltip>
);
})}
</Stack>
)}
</Stack>
<Box sx={{
color: "#475569",
lineHeight: 1.7,
fontSize: "0.9rem",
"& p": { m: 0, mb: 1.5 },
"& ul": { m: 0, mb: 1.5, pl: 2 }
}}>
{renderMarkdown(insight.content)}
</Box>
</Paper>
))}
</Stack>
</Box>
) : (
/* Fallback if keyInsights is missing but we have summary paragraphs */
research.summary && research.summary.length > 500 && !research.keyInsights && (
<Box sx={{ mb: 4 }}>
<Typography variant="h6" sx={{ mb: 2, color: "#0f172a", fontWeight: 700, display: "flex", alignItems: "center", gap: 1 }}>
<ArticleIcon sx={{ color: "#667eea" }} />
Additional Insights
</Typography>
<Paper
elevation={0}
sx={{
p: 2.5,
background: "#ffffff",
border: "1px solid rgba(0,0,0,0.06)",
boxShadow: "0 2px 12px rgba(0,0,0,0.03)",
borderRadius: 2,
}}
>
<Box sx={{
color: "#475569",
lineHeight: 1.7,
fontSize: "0.9rem",
}}>
{/* Render parts of summary that might contain insights if structured data is missing */}
{renderMarkdown(research.summary.split('\n\n').slice(1).join('\n\n'))}
</Box>
</Paper>
</Box>
)
)}
{/* Expert Quotes Section */}
{research.expertQuotes && research.expertQuotes.length > 0 && (
<Box sx={{ mt: 4, pt: 3, borderTop: "1px solid rgba(0,0,0,0.04)" }}>
<Typography variant="h6" sx={{ mb: 2, color: "#0f172a", fontWeight: 700, display: "flex", alignItems: "center", gap: 1 }}>
<FormatQuoteIcon sx={{ color: "#8b5cf6" }} />
Expert Quotes ({research.expertQuotes.length})
</Typography>
<Stack spacing={2}>
{research.expertQuotes.map((eq, idx) => (
<Paper
key={idx}
elevation={0}
sx={{
p: 2.5,
background: "linear-gradient(135deg, rgba(139, 92, 246, 0.04) 0%, rgba(99, 102, 241, 0.04) 100%)",
border: "1px solid rgba(139, 92, 246, 0.15)",
borderLeft: "4px solid #8b5cf6",
borderRadius: 2,
}}
>
<Stack direction="row" spacing={1.5} alignItems="flex-start">
<FormatQuoteIcon sx={{ color: "#8b5cf6", fontSize: "1.5rem", mt: -0.5, opacity: 0.7 }} />
<Box sx={{ flex: 1 }}>
<Typography variant="body2" sx={{ color: "#1e293b", fontStyle: "italic", lineHeight: 1.7, fontSize: "0.95rem" }}>
&ldquo;{eq.quote}&rdquo;
</Typography>
{eq.source_index !== undefined && (() => {
const fact = research.factCards[eq.source_index - 1];
const sourceUrl = fact?.url;
const hasUrl = !!sourceUrl;
const hue = (eq.source_index * 47 + 270) % 360;
const gradientFrom = `hsl(${hue}, 70%, 55%)`;
const gradientTo = `hsl(${(hue + 30) % 360}, 80%, 65%)`;
return (
<Box sx={{ mt: 1 }}>
<Tooltip title={hasUrl ? (
<Box sx={{ maxWidth: 300, wordBreak: "break-all" }}>
<Typography variant="caption" sx={{ color: "#fff", fontWeight: 600 }}>Source {eq.source_index}</Typography>
<br />
<Typography variant="caption" sx={{ color: "rgba(255,255,255,0.8)", fontSize: "0.65rem" }}>{sourceUrl}</Typography>
</Box>
) : `Source ${eq.source_index}`} arrow placement="top">
<Chip
label={hasUrl ? `Source ${eq.source_index}` : `Source ${eq.source_index}`}
size="small"
onClick={hasUrl ? () => window.open(sourceUrl, "_blank", "noopener,noreferrer") : undefined}
sx={{
height: 24,
fontSize: "0.7rem",
fontWeight: 800,
fontFamily: "'Inter', 'Roboto', monospace",
border: "none",
background: hasUrl
? `linear-gradient(135deg, ${gradientFrom}, ${gradientTo})`
: `linear-gradient(135deg, ${alpha(gradientFrom, 0.3)}, ${alpha(gradientTo, 0.3)})`,
color: hasUrl ? "#fff" : alpha("#fff", 0.7),
cursor: hasUrl ? "pointer" : "default",
borderRadius: "8px",
px: 1,
boxShadow: hasUrl
? `0 2px 8px ${alpha(gradientFrom, 0.35)}, inset 0 1px 0 ${alpha("#fff", 0.2)}`
: "none",
transition: "all 0.2s ease",
"&:hover": hasUrl ? {
background: `linear-gradient(135deg, ${gradientTo}, ${gradientFrom})`,
boxShadow: `0 4px 14px ${alpha(gradientFrom, 0.5)}, inset 0 1px 0 ${alpha("#fff", 0.3)}`,
transform: "translateY(-1px)",
} : {},
}}
/>
</Tooltip>
</Box>
);
})()}
</Box>
</Stack>
</Paper>
))}
</Stack>
</Box>
)}
{/* Search Queries Used */}
{research.searchQueries && research.searchQueries.length > 0 && (
<Box sx={{ mt: 4, pt: 3, borderTop: "1px solid rgba(0,0,0,0.04)" }}>
<Typography variant="subtitle2" sx={{ mb: 1.5, color: "#64748b", fontWeight: 700, fontSize: "0.7rem", textTransform: "uppercase", letterSpacing: "0.05em" }}>
Search Queries Used
</Typography>
<Stack direction="row" spacing={1} flexWrap="wrap" useFlexGap>
{research.searchQueries.map((query, idx) => (
<Chip
key={idx}
label={query}
size="small"
variant="outlined"
sx={{
borderColor: "rgba(102, 126, 234, 0.15)",
color: "#94a3b8",
background: alpha("#f8fafc", 0.3),
fontSize: "0.7rem",
borderRadius: 1,
}}
/>
))}
</Stack>
</Box>
)}
</Box>
{research.factCards.length > 0 && (
<>
<Divider sx={{ borderColor: "rgba(0,0,0,0.08)" }} />
<Stack direction="row" justifyContent="space-between" alignItems="center" sx={{ mb: 1.5, flexWrap: "wrap", gap: 1 }}>
<Typography variant="subtitle2" sx={{ color: "#0f172a", fontWeight: 600 }}>
Research Sources & Facts ({research.factCards.length})
</Typography>
<Typography variant="caption" sx={{ color: "#64748b", fontSize: "0.75rem" }}>
Click to expand Hover to see source
</Typography>
</Stack>
<Box
sx={{
display: "grid",
gridTemplateColumns: { xs: "1fr", sm: "repeat(2, 1fr)", md: "repeat(3, 1fr)", lg: "repeat(4, 1fr)" },
gap: 1.5,
width: "100%",
overflow: "hidden",
}}
>
{research.factCards.map((fact) => (
<FactCard key={fact.id} fact={fact} />
))}
</Box>
</>
)}
{/* Listener CTA Section */}
{research.listenerCta && research.listenerCta.length > 0 && (
<>
<Divider sx={{ borderColor: "rgba(0,0,0,0.08)" }} />
<Box>
<Typography variant="h6" sx={{ mb: 2, color: "#0f172a", fontWeight: 700, display: "flex", alignItems: "center", gap: 1 }}>
<CampaignIcon sx={{ color: "#f59e0b" }} />
Listener Call-to-Action Ideas ({research.listenerCta.length})
</Typography>
<Stack spacing={1.5}>
{research.listenerCta.map((cta, idx) => (
<Paper
key={idx}
elevation={0}
sx={{
p: 2,
background: "linear-gradient(135deg, rgba(245, 158, 11, 0.05) 0%, rgba(251, 191, 36, 0.05) 100%)",
border: "1px solid rgba(245, 158, 11, 0.15)",
borderRadius: 2,
display: "flex",
alignItems: "flex-start",
gap: 1.5,
}}
>
<Chip
label={`#${idx + 1}`}
size="small"
sx={{
bgcolor: alpha("#f59e0b", 0.15),
color: "#b45309",
fontWeight: 700,
fontSize: "0.7rem",
height: 24,
minWidth: 32,
}}
/>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.6, flex: 1, pt: 0.2 }}>
{cta}
</Typography>
</Paper>
))}
</Stack>
</Box>
</>
)}
{/* Mapped Angles Section */}
{research.mappedAngles && research.mappedAngles.length > 0 && (
<>
<Divider sx={{ borderColor: "rgba(0,0,0,0.08)" }} />
<Box>
<Typography variant="h6" sx={{ mb: 2, color: "#0f172a", fontWeight: 700, display: "flex", alignItems: "center", gap: 1 }}>
<ExploreIcon sx={{ color: "#06b6d4" }} />
Content Angles ({research.mappedAngles.length})
</Typography>
<Stack spacing={2}>
{research.mappedAngles.map((angle, idx) => (
<Paper
key={idx}
elevation={0}
sx={{
p: 2.5,
background: "#ffffff",
border: "1px solid rgba(0,0,0,0.06)",
borderLeft: "4px solid #06b6d4",
boxShadow: "0 2px 12px rgba(0,0,0,0.03)",
borderRadius: 2,
}}
>
<Stack direction="row" justifyContent="space-between" alignItems="flex-start" sx={{ mb: 1 }}>
<Typography variant="subtitle1" sx={{ color: "#0f172a", fontWeight: 700 }}>
{angle.title}
</Typography>
{angle.mappedFactIds && angle.mappedFactIds.length > 0 && (
<Stack direction="row" spacing={0.5}>
{angle.mappedFactIds.slice(0, 4).map((fid: string) => (
<Chip
key={fid}
label={fid.replace("fact_", "F")}
size="small"
variant="outlined"
sx={{
height: 18,
fontSize: "0.6rem",
fontWeight: 700,
borderColor: alpha("#06b6d4", 0.3),
color: "#06b6d4",
bgcolor: alpha("#06b6d4", 0.05),
}}
/>
))}
{angle.mappedFactIds.length > 4 && (
<Chip
label={`+${angle.mappedFactIds.length - 4}`}
size="small"
sx={{ height: 18, fontSize: "0.6rem", color: "#64748b" }}
/>
)}
</Stack>
)}
</Stack>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.7, fontSize: "0.9rem" }}>
{angle.why}
</Typography>
</Paper>
))}
</Stack>
</Box>
</>
)}
</Stack>
</GlassyCard>
);
};

View File

@@ -0,0 +1,811 @@
import React, { useState, useEffect } from "react";
import { Stack, Box, Typography, Divider, Chip, alpha, CircularProgress, LinearProgress, IconButton, Tooltip } from "@mui/material";
import {
EditNote as EditNoteIcon,
CheckCircle as CheckCircleIcon,
RadioButtonUnchecked as RadioButtonUncheckedIcon,
VolumeUp as VolumeUpIcon,
PlayArrow as PlayArrowIcon,
Image as ImageIcon,
Delete as DeleteIcon,
} from "@mui/icons-material";
import { Scene, Line, Knobs } from "../types";
import { GlassyCard, glassyCardSx, PrimaryButton } from "../ui";
import { LineEditor } from "./LineEditor";
import { ImageRegenerateModal, ImageGenerationSettings } from "./ImageRegenerateModal";
import { AudioRegenerateModal, AudioGenerationSettings } from "./AudioRegenerateModal";
import { podcastApi } from "../../../services/podcastApi";
import { aiApiClient } from "../../../api/client";
import { getCachedMedia, setCachedMedia } from "../../../utils/mediaCache";
interface SceneEditorProps {
scene: Scene;
onUpdateScene: (s: Scene) => void;
onApprove: (id: string) => Promise<void>;
onDelete: (sceneId: string) => void;
knobs: Knobs;
approvingSceneId?: string | null;
generatingAudioId?: string | null;
onAudioGenerationStart?: (sceneId: string) => void;
onAudioGenerated?: (sceneId: string, audioUrl: string) => void;
idea?: string; // Podcast idea for image generation context
avatarUrl?: string | null; // Base avatar URL for consistent scene image generation
totalScenes?: number; // Total number of scenes in the script
}
export const SceneEditor: React.FC<SceneEditorProps> = ({
scene,
onUpdateScene,
onApprove,
onDelete,
knobs,
approvingSceneId,
generatingAudioId,
onAudioGenerationStart,
onAudioGenerated,
idea,
avatarUrl,
totalScenes,
}) => {
const [localGenerating, setLocalGenerating] = useState(false);
const [generatingImage, setGeneratingImage] = useState(false);
const [imageGenerationStatus, setImageGenerationStatus] = useState<string>("");
const [imageGenerationProgress, setImageGenerationProgress] = useState<number>(0);
const [audioBlobUrl, setAudioBlobUrl] = useState<string | null>(null);
const [imageBlobUrl, setImageBlobUrl] = useState<string | null>(null);
const [imageLoading, setImageLoading] = useState(false);
const [showRegenerateModal, setShowRegenerateModal] = useState(false);
const [showAudioModal, setShowAudioModal] = useState(false);
const [audioSettings, setAudioSettings] = useState<AudioGenerationSettings>({
voiceId: "Wise_Woman",
speed: 1.0,
volume: 1.0,
pitch: 0.0,
emotion: scene.emotion || "neutral",
englishNormalization: true,
sampleRate: 24000,
bitrate: 64000,
channel: "1",
format: "mp3",
languageBoost: "auto",
});
// Load audio as blob when audioUrl is available
useEffect(() => {
if (!scene.audioUrl) {
// Clean up blob URL if audioUrl is removed
setAudioBlobUrl((currentBlobUrl) => {
if (currentBlobUrl) {
URL.revokeObjectURL(currentBlobUrl);
}
return null;
});
return;
}
let isMounted = true;
const currentAudioUrl = scene.audioUrl; // Capture current value
const loadAudioBlob = async () => {
try {
// Normalize path
let audioPath = currentAudioUrl.startsWith('/') ? currentAudioUrl : `/${currentAudioUrl}`;
// Convert /api/story/audio/ to /api/podcast/audio/ if needed
if (audioPath.includes('/api/story/audio/')) {
const filename = audioPath.split('/api/story/audio/').pop() || '';
audioPath = `/api/podcast/audio/${filename}`;
}
// Ensure it's a podcast audio endpoint
if (!audioPath.includes('/api/podcast/audio/')) {
const filename = audioPath.split('/').pop() || currentAudioUrl;
audioPath = `/api/podcast/audio/${filename}`;
}
// Remove query parameters if present
audioPath = audioPath.split('?')[0];
const response = await aiApiClient.get(audioPath, {
responseType: 'blob',
});
if (!isMounted) {
// Component unmounted or audioUrl changed, don't set blob URL
return;
}
// Double-check that audioUrl hasn't changed
if (scene.audioUrl !== currentAudioUrl) {
return;
}
const blob = response.data;
const blobUrl = URL.createObjectURL(blob);
setAudioBlobUrl((prevBlobUrl) => {
// Clean up previous blob URL if exists
if (prevBlobUrl && prevBlobUrl !== blobUrl) {
URL.revokeObjectURL(prevBlobUrl);
}
return blobUrl;
});
} catch (error) {
console.error(`Failed to load audio blob for scene ${scene.id}:`, error);
// Don't set blob URL on error - will show error state
}
};
loadAudioBlob();
// Cleanup: only mark as unmounted, don't revoke blob URL here
// The blob URL will be cleaned up when audioUrl changes (new effect) or component unmounts
return () => {
isMounted = false;
};
}, [scene.audioUrl, scene.id]);
// Load image as blob when imageUrl is available
useEffect(() => {
if (!scene.imageUrl) {
// Clean up blob URL if imageUrl is removed
setImageBlobUrl((currentBlobUrl) => {
if (currentBlobUrl && currentBlobUrl.startsWith('blob:')) {
URL.revokeObjectURL(currentBlobUrl);
}
return null;
});
return;
}
// Check cache first with scene context
const cachedUrl = getCachedMedia(scene.imageUrl, scene.id);
if (cachedUrl) {
console.log('[SceneEditor] Using cached image:', scene.imageUrl, `(scene: ${scene.id})`);
setImageBlobUrl(cachedUrl);
setImageLoading(false);
return;
}
let isMounted = true;
const currentImageUrl = scene.imageUrl; // Capture current value
const loadImageBlob = async () => {
try {
setImageLoading(true);
// Check cache again in case it was loaded while we were waiting
const cachedUrl = getCachedMedia(currentImageUrl, scene.id);
if (cachedUrl) {
if (isMounted) {
setImageBlobUrl(cachedUrl);
setImageLoading(false);
}
return;
}
console.log('[SceneEditor] Loading image blob for:', currentImageUrl);
// Normalize path
let imagePath = currentImageUrl.startsWith('/') ? currentImageUrl : `/${currentImageUrl}`;
// Convert /api/story/images/ to /api/podcast/images/ if needed
if (imagePath.includes('/api/story/images/')) {
const filename = imagePath.split('/api/story/images/').pop() || '';
imagePath = `/api/podcast/images/${filename}`;
}
// Ensure it's a podcast image endpoint
if (!imagePath.includes('/api/podcast/images/')) {
const filename = imagePath.split('/').pop() || currentImageUrl;
imagePath = `/api/podcast/images/${filename}`;
}
// Remove query parameters if present
imagePath = imagePath.split('?')[0];
const response = await aiApiClient.get(imagePath, {
responseType: 'blob',
});
if (!isMounted) {
return;
}
// Double-check that imageUrl hasn't changed
if (scene.imageUrl !== currentImageUrl) {
return;
}
const blob = response.data;
const blobUrl = URL.createObjectURL(blob);
// Cache the blob URL with scene context
setCachedMedia(currentImageUrl, blobUrl, 'image', blob.size, scene.id);
setImageBlobUrl((prevBlobUrl) => {
// Clean up previous blob URL if exists
if (prevBlobUrl && prevBlobUrl !== blobUrl && prevBlobUrl.startsWith('blob:')) {
URL.revokeObjectURL(prevBlobUrl);
}
return blobUrl;
});
console.log('[SceneEditor] Image blob loaded and cached successfully:', currentImageUrl);
} catch (error) {
console.error('[SceneEditor] Failed to load image blob:', error);
if (isMounted) {
// Try adding query token as fallback
try {
const token = localStorage.getItem('clerk_dashboard_token') || '';
if (token) {
const urlWithToken = `${currentImageUrl}?token=${encodeURIComponent(token)}`;
setImageBlobUrl(urlWithToken);
setCachedMedia(currentImageUrl, urlWithToken, 'image', undefined, scene.id);
}
} catch (fallbackError) {
console.error('[SceneEditor] Fallback image loading failed:', fallbackError);
}
}
} finally {
if (isMounted) {
setImageLoading(false);
}
}
};
loadImageBlob();
return () => {
isMounted = false;
// Don't cleanup blob URL here - let the cache handle it
};
}, [scene.imageUrl]);
const updateLine = (updatedLine: Line) => {
const updated = { ...scene, lines: scene.lines.map((l) => (l.id === updatedLine.id ? updatedLine : l)) };
onUpdateScene(updated);
};
const approving = approvingSceneId === scene.id;
const generating = generatingAudioId === scene.id || localGenerating;
const hasAudio = Boolean(scene.audioUrl && audioBlobUrl);
const hasImage = Boolean(scene.imageUrl);
const handleApproveAndGenerate = async (settings?: AudioGenerationSettings) => {
const wasAlreadyApproved = scene.approved;
const sceneId = scene.id;
try {
// Set generating state
setLocalGenerating(true);
if (onAudioGenerationStart) {
onAudioGenerationStart(sceneId);
}
// If scene is not approved yet, approve it first
// This will update the parent script state
if (!scene.approved) {
await onApprove(sceneId);
// The parent's approveScene already updated the script state
// We need to wait for React to propagate the updated scene prop
// For now, we'll update it locally too to ensure UI updates immediately
onUpdateScene({ ...scene, approved: true });
}
// Use the current scene (which should now be approved)
// If scene prop hasn't updated yet, use the local update we just made
const currentScene = { ...scene, approved: true };
// Generate audio
const effectiveSettings = settings || audioSettings;
const result = await podcastApi.renderSceneAudio({
scene: currentScene,
voiceId: effectiveSettings.voiceId || "Wise_Woman",
emotion: effectiveSettings.emotion || scene.emotion || knobs.voice_emotion || "neutral",
speed: effectiveSettings.speed ?? knobs.voice_speed ?? 1.0,
volume: effectiveSettings.volume ?? 1.0,
pitch: effectiveSettings.pitch ?? 0.0,
englishNormalization: effectiveSettings.englishNormalization ?? true,
sampleRate: effectiveSettings.sampleRate,
bitrate: effectiveSettings.bitrate,
channel: effectiveSettings.channel,
format: effectiveSettings.format,
languageBoost: effectiveSettings.languageBoost,
});
// Update scene with audio URL and ensure approved state
// This will sync with parent script state
const updatedScene = { ...currentScene, audioUrl: result.audioUrl, approved: true };
onUpdateScene(updatedScene);
if (onAudioGenerated) {
onAudioGenerated(sceneId, result.audioUrl);
}
} catch (error) {
console.error("Failed to approve and generate audio:", error);
// On error, revert approval only if we just approved it in this call
if (!wasAlreadyApproved) {
onUpdateScene({ ...scene, approved: false, audioUrl: undefined });
}
throw error;
} finally {
setLocalGenerating(false);
}
};
const handleGenerateImage = async (settings?: ImageGenerationSettings) => {
const sceneId = scene.id;
const startTime = Date.now();
let progressInterval: NodeJS.Timeout | null = null;
try {
setGeneratingImage(true);
setShowRegenerateModal(false);
setImageGenerationStatus("Submitting image generation request...");
setImageGenerationProgress(10);
// Build scene content from lines for context
const sceneContent = scene.lines.map((line) => line.text).join(" ");
// Log avatar URL for debugging
console.log("[SceneEditor] Generating image with avatarUrl:", avatarUrl);
console.log("[SceneEditor] Custom settings:", settings);
// Simulate progress updates during API call
progressInterval = setInterval(() => {
const elapsed = Date.now() - startTime;
const seconds = Math.floor(elapsed / 1000);
// Update status based on elapsed time
if (seconds < 5) {
setImageGenerationStatus("Submitting request to AI service...");
setImageGenerationProgress(15);
} else if (seconds < 15) {
setImageGenerationStatus("AI is generating your image...");
setImageGenerationProgress(30);
} else if (seconds < 30) {
setImageGenerationStatus("Creating character-consistent scene image...");
setImageGenerationProgress(50);
} else if (seconds < 60) {
setImageGenerationStatus("Rendering image details...");
setImageGenerationProgress(70);
} else {
setImageGenerationStatus(`Processing... (${seconds}s elapsed)`);
setImageGenerationProgress(Math.min(90, 50 + (seconds - 30) / 2));
}
}, 1000);
const result = await podcastApi.generateSceneImage({
sceneId: scene.id,
sceneTitle: scene.title,
sceneContent: sceneContent,
baseAvatarUrl: avatarUrl || undefined, // Pass base avatar URL for character consistency
idea: idea,
width: 1024,
height: 1024,
// Pass custom settings if provided
customPrompt: settings?.prompt,
style: settings?.style,
renderingSpeed: settings?.renderingSpeed,
aspectRatio: settings?.aspectRatio,
});
if (progressInterval) {
clearInterval(progressInterval);
progressInterval = null;
}
setImageGenerationStatus("Finalizing image...");
setImageGenerationProgress(95);
// Update scene with image URL
const updatedScene = { ...scene, imageUrl: result.image_url };
onUpdateScene(updatedScene);
const elapsed = Math.floor((Date.now() - startTime) / 1000);
setImageGenerationStatus(`Image generated successfully in ${elapsed}s`);
setImageGenerationProgress(100);
// Clear status after a moment
setTimeout(() => {
setImageGenerationStatus("");
setImageGenerationProgress(0);
}, 2000);
} catch (error: any) {
// Clear interval on error
if (progressInterval) {
clearInterval(progressInterval);
progressInterval = null;
}
console.error("Failed to generate image:", error);
// Extract error message from response if available
const errorMessage = error?.response?.data?.detail?.message
|| error?.response?.data?.detail?.error
|| error?.response?.data?.detail
|| error?.message
|| "Failed to generate image. Please try again.";
console.error("Error details:", {
status: error?.response?.status,
statusText: error?.response?.statusText,
data: error?.response?.data,
message: errorMessage,
});
setImageGenerationStatus(`Error: ${errorMessage}`);
setImageGenerationProgress(0);
// Show user-friendly error message
alert(`Image generation failed: ${errorMessage}`);
throw error;
} finally {
// Ensure interval is cleared
if (progressInterval) {
clearInterval(progressInterval);
}
setGeneratingImage(false);
}
};
const handleRegenerateClick = () => {
setShowRegenerateModal(true);
};
const handleAudioRegenerateClick = () => {
if (hasAudio) {
setShowAudioModal(true);
} else {
handleApproveAndGenerate(audioSettings);
}
};
const handleAudioRegenerate = (settings: AudioGenerationSettings) => {
setAudioSettings(settings);
setShowAudioModal(false);
handleApproveAndGenerate(settings);
};
return (
<GlassyCard sx={glassyCardSx}>
<Stack spacing={2.5}>
<Stack direction="row" justifyContent="space-between" alignItems="flex-start">
<Box sx={{ flex: 1 }}>
<Typography
variant="h6"
sx={{
display: "flex",
alignItems: "center",
gap: 1.5,
mb: 1,
color: "#0f172a",
fontWeight: 600,
fontSize: "1.25rem",
letterSpacing: "-0.01em",
}}
>
<EditNoteIcon fontSize="small" sx={{ color: "#667eea", fontSize: "1.5rem" }} />
{scene.title}
</Typography>
<Stack direction="row" spacing={1.5} alignItems="center" flexWrap="wrap">
<Chip
icon={scene.approved ? <CheckCircleIcon /> : <RadioButtonUncheckedIcon />}
label={scene.approved ? "Approved" : "Pending Approval"}
size="small"
color={scene.approved ? "success" : "warning"}
sx={{
background: scene.approved
? "linear-gradient(135deg, rgba(16, 185, 129, 0.12) 0%, rgba(5, 150, 105, 0.12) 100%)"
: "linear-gradient(135deg, rgba(245, 158, 11, 0.12) 0%, rgba(217, 119, 6, 0.12) 100%)",
color: scene.approved ? "#059669" : "#d97706",
border: scene.approved
? "1px solid rgba(16, 185, 129, 0.25)"
: "1px solid rgba(245, 158, 11, 0.25)",
fontWeight: 600,
fontSize: "0.75rem",
height: 26,
boxShadow: "0 1px 2px rgba(0, 0, 0, 0.05)",
}}
/>
<Typography variant="caption" sx={{ color: "#64748b", fontWeight: 500, fontSize: "0.8125rem" }}>
Duration: {scene.duration}s
</Typography>
</Stack>
</Box>
<Stack direction="row" spacing={1.5} flexWrap="wrap" useFlexGap>
<PrimaryButton
onClick={handleAudioRegenerateClick}
disabled={approving || generating}
loading={approving || generating}
startIcon={
hasAudio && !generating ? (
<VolumeUpIcon />
) : generating ? (
<CircularProgress size={16} sx={{ color: "white" }} />
) : (
<PlayArrowIcon />
)
}
tooltip={
hasAudio && !generating
? "Regenerate audio for this scene with custom settings"
: generating
? "Generating audio..."
: scene.approved
? "Generate audio for this scene"
: "Approve scene and generate audio"
}
sx={{
minWidth: 200,
}}
>
{hasAudio && !generating
? "Regenerate Audio"
: generating
? "Generating Audio..."
: scene.approved
? "Generate Audio"
: "Approve & Generate Audio"}
</PrimaryButton>
<PrimaryButton
onClick={hasImage ? handleRegenerateClick : () => handleGenerateImage()}
disabled={generatingImage}
loading={generatingImage}
startIcon={
hasImage && !generatingImage ? (
<ImageIcon />
) : generatingImage ? (
<CircularProgress size={16} sx={{ color: "white" }} />
) : (
<ImageIcon />
)
}
tooltip={
hasImage
? "Regenerate image for this scene"
: generatingImage
? "Generating image..."
: "Generate image for video (optional)"
}
sx={{
minWidth: 180,
background: hasImage
? "linear-gradient(135deg, #10b981 0%, #059669 100%)"
: "linear-gradient(135deg, #667eea 0%, #764ba2 100%)",
"&:hover": {
background: hasImage
? "linear-gradient(135deg, #059669 0%, #047857 100%)"
: "linear-gradient(135deg, #764ba2 0%, #667eea 100%)",
},
}}
>
{hasImage && !generatingImage
? "Regenerate Image"
: generatingImage
? "Generating Image..."
: "Generate Image"}
</PrimaryButton>
<Tooltip title={totalScenes && totalScenes <= 1 ? "Cannot delete the last scene" : "Delete this scene"}>
<IconButton
onClick={() => onDelete(scene.id)}
disabled={approving || generating || (totalScenes !== undefined && totalScenes <= 1)}
sx={{
color: "#ef4444",
backgroundColor: "rgba(239, 68, 68, 0.1)",
border: "1px solid rgba(239, 68, 68, 0.2)",
borderRadius: 2,
padding: 1.5,
"&:hover": {
backgroundColor: "rgba(239, 68, 68, 0.15)",
borderColor: "rgba(239, 68, 68, 0.3)",
},
"&:disabled": {
backgroundColor: "rgba(156, 163, 175, 0.1)",
borderColor: "rgba(156, 163, 175, 0.2)",
color: "#9ca3af",
},
}}
>
<DeleteIcon sx={{ fontSize: "1.25rem" }} />
</IconButton>
</Tooltip>
</Stack>
</Stack>
<Divider sx={{ borderColor: "rgba(15, 23, 42, 0.08)", borderWidth: 1 }} />
<Stack spacing={2}>
{scene.lines.map((line) => (
<LineEditor key={line.id} line={line} onChange={updateLine} />
))}
</Stack>
{scene.audioUrl && (
<>
<Divider sx={{ borderColor: "rgba(15, 23, 42, 0.08)", borderWidth: 1, mt: 1 }} />
<Box
sx={{
p: 2,
background: hasAudio
? "linear-gradient(135deg, rgba(16, 185, 129, 0.08) 0%, rgba(5, 150, 105, 0.08) 100%)"
: "linear-gradient(135deg, rgba(245, 158, 11, 0.08) 0%, rgba(217, 119, 6, 0.08) 100%)",
borderRadius: 2,
border: hasAudio
? "1px solid rgba(16, 185, 129, 0.2)"
: "1px solid rgba(245, 158, 11, 0.2)",
}}
>
<Stack direction="row" alignItems="center" spacing={1.5} sx={{ mb: 1.5 }}>
<VolumeUpIcon sx={{ color: hasAudio ? "#059669" : "#d97706", fontSize: "1.25rem" }} />
<Typography variant="subtitle2" sx={{ color: hasAudio ? "#059669" : "#d97706", fontWeight: 600 }}>
{hasAudio ? "Audio Generated" : "Loading Audio..."}
</Typography>
</Stack>
{hasAudio && audioBlobUrl ? (
<audio controls style={{ width: "100%", borderRadius: 8 }}>
<source src={audioBlobUrl} type="audio/mpeg" />
Your browser does not support the audio element.
</audio>
) : (
<Box sx={{ display: "flex", alignItems: "center", justifyContent: "center", py: 2 }}>
<CircularProgress size={24} sx={{ color: "#d97706" }} />
</Box>
)}
</Box>
</>
)}
{/* Image Generation Progress - Show when generating */}
{generatingImage && (
<>
<Divider sx={{ borderColor: "rgba(15, 23, 42, 0.08)", borderWidth: 1, mt: 1 }} />
<Box
sx={{
p: 2,
background: "linear-gradient(135deg, rgba(102, 126, 234, 0.08) 0%, rgba(118, 75, 162, 0.08) 100%)",
borderRadius: 2,
border: "1px solid rgba(102, 126, 234, 0.2)",
}}
>
<Stack direction="row" alignItems="center" spacing={1.5} sx={{ mb: 1.5 }}>
<ImageIcon sx={{ color: "#667eea", fontSize: "1.25rem" }} />
<Typography variant="subtitle2" sx={{ color: "#667eea", fontWeight: 600 }}>
Generating Image...
</Typography>
</Stack>
{/* Progress Bar */}
<Box sx={{ mb: 1.5 }}>
<LinearProgress
variant="determinate"
value={imageGenerationProgress}
sx={{
height: 8,
borderRadius: 4,
backgroundColor: alpha("#667eea", 0.1),
"& .MuiLinearProgress-bar": {
backgroundColor: "#667eea",
borderRadius: 4,
}
}}
/>
<Typography variant="caption" sx={{ color: "#667eea", mt: 0.5, display: "block", textAlign: "right" }}>
{imageGenerationProgress}%
</Typography>
</Box>
{/* Status Message */}
{imageGenerationStatus && (
<Typography variant="body2" sx={{ color: "#667eea", fontSize: "0.875rem", lineHeight: 1.6, mb: 1 }}>
{imageGenerationStatus}
</Typography>
)}
{/* Spinner */}
<Box sx={{ display: "flex", alignItems: "center", justifyContent: "center", mt: 1 }}>
<CircularProgress size={32} sx={{ color: "#667eea" }} />
</Box>
</Box>
</>
)}
{/* Generated Image Display - Show when image exists and not generating */}
{scene.imageUrl && !generatingImage && (
<>
<Divider sx={{ borderColor: "rgba(15, 23, 42, 0.08)", borderWidth: 1, mt: 1 }} />
<Box
sx={{
p: 2,
background: imageBlobUrl && !imageLoading
? "linear-gradient(135deg, rgba(102, 126, 234, 0.08) 0%, rgba(118, 75, 162, 0.08) 100%)"
: "linear-gradient(135deg, rgba(245, 158, 11, 0.08) 0%, rgba(217, 119, 6, 0.08) 100%)",
borderRadius: 2,
border: imageBlobUrl && !imageLoading
? "1px solid rgba(102, 126, 234, 0.2)"
: "1px solid rgba(245, 158, 11, 0.2)",
}}
>
<Stack direction="row" alignItems="center" spacing={1.5} sx={{ mb: 1.5 }}>
<ImageIcon sx={{ color: imageBlobUrl && !imageLoading ? "#667eea" : "#d97706", fontSize: "1.25rem" }} />
<Typography variant="subtitle2" sx={{ color: imageBlobUrl && !imageLoading ? "#667eea" : "#d97706", fontWeight: 600 }}>
{imageBlobUrl && !imageLoading ? "Image Generated" : "Loading Image..."}
</Typography>
</Stack>
{imageBlobUrl && !imageLoading ? (
<Box
sx={{
width: "100%",
borderRadius: 2,
overflow: "hidden",
border: "1px solid rgba(102,126,234,0.2)",
background: alpha("#667eea", 0.05),
}}
>
<Box
component="img"
src={imageBlobUrl}
alt={scene.title}
sx={{
width: "100%",
height: "auto",
display: "block",
maxHeight: 400,
objectFit: "cover",
}}
onError={(e) => {
console.error('[SceneEditor] Image failed to load:', {
src: e.currentTarget.src,
imageUrl: scene.imageUrl,
imageBlobUrl,
});
}}
onLoad={() => {
console.log('[SceneEditor] Image loaded successfully');
}}
/>
</Box>
) : (
<Box sx={{ display: "flex", alignItems: "center", justifyContent: "center", py: 2 }}>
<CircularProgress size={24} sx={{ color: "#d97706" }} />
</Box>
)}
</Box>
</>
)}
</Stack>
{/* Image Regeneration Modal */}
<ImageRegenerateModal
open={showRegenerateModal}
onClose={() => setShowRegenerateModal(false)}
onRegenerate={handleGenerateImage}
initialPrompt={(() => {
const promptParts = [
`Scene: ${scene.title}`,
"Professional podcast recording studio",
"Modern microphone setup",
"Clean background, professional lighting",
"16:9 aspect ratio, video-optimized composition"
];
if (idea) {
promptParts.push(`Topic: ${idea.substring(0, 60)}`);
}
return promptParts.join(", ");
})()}
initialStyle="Realistic"
initialRenderingSpeed="Quality"
initialAspectRatio="16:9"
isGenerating={generatingImage}
/>
<AudioRegenerateModal
open={showAudioModal}
onClose={() => setShowAudioModal(false)}
onRegenerate={handleAudioRegenerate}
initialSettings={audioSettings}
isGenerating={generating}
/>
</GlassyCard>
);
};

View File

@@ -0,0 +1,818 @@
import React, { useEffect, useState, useCallback } from "react";
import { Box, Stack, Typography, Alert, Paper, LinearProgress, CircularProgress, alpha, Collapse, IconButton, Divider } from "@mui/material";
import { EditNote as EditNoteIcon, CheckCircle as CheckCircleIcon, PlayArrow as PlayArrowIcon, ArrowBack as ArrowBackIcon, Info as InfoIcon, ExpandMore as ExpandMoreIcon, ExpandLess as ExpandLessIcon, Download as DownloadIcon, Refresh as RefreshIcon } from "@mui/icons-material";
import { Script, Knobs, Scene } from "../types";
import { BlogResearchResponse } from "../../../services/blogWriterApi";
import { podcastApi } from "../../../services/podcastApi";
import { GlassyCard, PrimaryButton, SecondaryButton } from "../ui";
import { SceneEditor } from "./SceneEditor";
import { InlineAudioPlayer } from "../InlineAudioPlayer";
import { aiApiClient } from "../../../api/client";
interface ScriptEditorProps {
projectId: string;
idea: string;
research: any; // Research type
rawResearch: BlogResearchResponse | null;
knobs: Knobs;
speakers: number;
durationMinutes: number;
script: Script | null;
onScriptChange: (script: Script) => void;
onBackToResearch: () => void;
onProceedToRendering: (script: Script) => void;
onError: (message: string) => void;
avatarUrl?: string | null; // Base avatar URL for consistent scene image generation
analysis?: any;
outline?: any;
}
export const ScriptEditor: React.FC<ScriptEditorProps> = ({
projectId,
idea,
research,
rawResearch,
knobs,
speakers,
durationMinutes,
script: initialScript,
onScriptChange,
onBackToResearch,
onProceedToRendering,
onError,
avatarUrl,
analysis,
outline,
}) => {
const [script, setScript] = useState<Script | null>(initialScript);
const [loading, setLoading] = useState(false);
const [error, setError] = useState<string | null>(null);
const [approvingSceneId, setApprovingSceneId] = useState<string | null>(null);
const [generatingAudioId, setGeneratingAudioId] = useState<string | null>(null);
const [showScriptFormatInfo, setShowScriptFormatInfo] = useState(true);
const [combiningAudio, setCombiningAudio] = useState(false);
const [combinedAudioResult, setCombinedAudioResult] = useState<{
url: string;
filename: string;
duration: number;
sceneCount: number;
} | null>(null);
// Defer upward script updates to avoid setState during render warnings
const emitScriptChange = useCallback(
(next: Script) => Promise.resolve().then(() => onScriptChange(next)),
[onScriptChange]
);
// Sync with parent state
useEffect(() => {
if (initialScript) {
setScript(initialScript);
}
}, [initialScript]);
useEffect(() => {
// If script already exists, don't regenerate
if (script) {
return;
}
// Only generate if we have research data
if (!rawResearch) {
return;
}
let mounted = true;
setLoading(true);
setError(null);
podcastApi
.generateScript({
projectId,
idea,
research: rawResearch,
knobs,
speakers,
durationMinutes,
analysis,
outline,
})
.then((res) => {
if (mounted) {
setScript(res);
emitScriptChange(res);
setError(null);
}
})
.catch((err) => {
const message = err instanceof Error ? err.message : "Failed to generate script";
setError(message);
onError(message);
})
.finally(() => mounted && setLoading(false));
return () => {
mounted = false;
};
}, [projectId, rawResearch, idea, knobs, speakers, durationMinutes, analysis, outline, emitScriptChange, onError, script]);
const updateScene = (updated: Scene) => {
// Use functional update to ensure we're working with latest state
setScript((currentScript) => {
if (!currentScript) return currentScript;
const updatedScript = {
...currentScript,
scenes: currentScript.scenes.map((s) => (s.id === updated.id ? { ...s, ...updated } : s))
};
emitScriptChange(updatedScript);
return updatedScript;
});
};
const approveScene = async (sceneId: string) => {
try {
setApprovingSceneId(sceneId);
await podcastApi.approveScene({ projectId, sceneId });
// Use functional update to ensure we're working with latest state
setScript((currentScript) => {
if (!currentScript) return currentScript;
const updatedScript = {
...currentScript,
scenes: currentScript.scenes.map((s) => (s.id === sceneId ? { ...s, approved: true } : s)),
};
emitScriptChange(updatedScript);
return updatedScript;
});
} catch (err) {
const message = err instanceof Error ? err.message : "Failed to approve scene";
setError(message);
onError(message);
throw err;
} finally {
setApprovingSceneId((current) => (current === sceneId ? null : current));
}
};
const deleteScene = useCallback((sceneId: string) => {
if (!script) return;
// Prevent deleting if it's the last scene
if (script.scenes.length <= 1) {
onError("Cannot delete the last scene. At least one scene is required.");
return;
}
// Add confirmation dialog
const sceneToDelete = script.scenes.find(s => s.id === sceneId);
if (!sceneToDelete) return;
const confirmDelete = window.confirm(
`Are you sure you want to delete "${sceneToDelete.title}"? This action cannot be undone.`
);
if (!confirmDelete) return;
// Remove the scene from the script
const updatedScenes = script.scenes.filter(s => s.id !== sceneId);
const updatedScript = { ...script, scenes: updatedScenes };
emitScriptChange(updatedScript);
setScript(updatedScript);
// Show success message
console.log(`[ScriptEditor] Scene "${sceneToDelete.title}" deleted successfully`);
}, [script, emitScriptChange, onError]);
const allApproved = script && script.scenes.every((s) => s.approved);
const approvedCount = script ? script.scenes.filter((s) => s.approved).length : 0;
const totalScenes = script ? script.scenes.length : 0;
// Check if all scenes have both audio and images (required for video rendering)
const allScenesHaveAudioAndImages = script && script.scenes.every((s) => s.audioUrl && s.imageUrl);
const scenesWithAudio = script ? script.scenes.filter((s) => s.audioUrl).length : 0;
const allScenesHaveAudio = script && script.scenes.every((s) => s.audioUrl);
const combineAudio = useCallback(async () => {
if (!script || !projectId) return;
try {
setCombiningAudio(true);
const sceneIds: string[] = [];
const sceneAudioUrls: string[] = [];
script.scenes.forEach((scene) => {
if (scene.audioUrl) {
// Ensure we're using the correct URL format (not blob URLs)
const audioUrl = scene.audioUrl.startsWith('blob:') ? '' : scene.audioUrl;
if (audioUrl) {
sceneIds.push(scene.id);
sceneAudioUrls.push(audioUrl);
}
}
});
if (sceneIds.length === 0) {
onError("No audio files found to combine.");
return;
}
const result = await podcastApi.combineAudio({
projectId,
sceneIds,
sceneAudioUrls,
});
// Store combined audio result for preview
setCombinedAudioResult({
url: result.combined_audio_url,
filename: result.combined_audio_filename,
duration: result.total_duration,
sceneCount: result.scene_count,
});
// Download the combined audio as blob (for authenticated endpoints)
try {
// Normalize path
let audioPath = result.combined_audio_url.startsWith('/')
? result.combined_audio_url
: `/${result.combined_audio_url}`;
// Ensure it's a podcast audio endpoint
if (!audioPath.includes('/api/podcast/audio/')) {
const filename = audioPath.split('/').pop() || result.combined_audio_filename;
audioPath = `/api/podcast/audio/${filename}`;
}
// Remove query parameters if present
audioPath = audioPath.split('?')[0];
// Fetch as blob using authenticated client
const response = await aiApiClient.get(audioPath, {
responseType: 'blob',
});
// Create blob URL and download
const blob = response.data;
const blobUrl = URL.createObjectURL(blob);
const link = document.createElement("a");
link.href = blobUrl;
link.download = result.combined_audio_filename || `podcast-episode-${projectId.slice(-8)}.mp3`;
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
// Clean up blob URL after a delay
setTimeout(() => {
URL.revokeObjectURL(blobUrl);
}, 100);
} catch (downloadError) {
console.error('Failed to download combined audio:', downloadError);
onError('Failed to download audio file. You can try downloading again from the preview.');
}
} catch (error) {
const message = error instanceof Error ? error.message : "Failed to combine audio";
onError(`Failed to combine audio: ${message}`);
} finally {
setCombiningAudio(false);
}
}, [script, projectId, onError]);
return (
<Box sx={{ mt: 4 }}>
<Stack direction="row" spacing={2} alignItems="center" sx={{ mb: 4 }}>
<SecondaryButton onClick={onBackToResearch} startIcon={<ArrowBackIcon />}>
Back to Research
</SecondaryButton>
<Box sx={{ flex: 1 }}>
<Typography
variant="h4"
sx={{
background: "linear-gradient(135deg, #667eea 0%, #764ba2 100%)",
WebkitBackgroundClip: "text",
WebkitTextFillColor: "transparent",
fontWeight: 700,
letterSpacing: "-0.02em",
display: "flex",
alignItems: "center",
gap: 1.5,
fontSize: { xs: "1.75rem", md: "2rem" },
}}
>
<EditNoteIcon sx={{ fontSize: "2rem" }} />
Script Editor
</Typography>
<Typography variant="body2" sx={{ color: "#64748b", mt: 0.5, ml: 5.5 }}>
Review and refine your podcast script before rendering
</Typography>
</Box>
</Stack>
{loading && (
<Alert
severity="info"
icon={<CircularProgress size={20} />}
sx={{
mb: 3,
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.08) 0%, rgba(139, 92, 246, 0.08) 100%)",
border: "1px solid rgba(99, 102, 241, 0.2)",
borderRadius: 2,
boxShadow: "0 1px 2px rgba(99, 102, 241, 0.05)",
"& .MuiAlert-icon": {
color: "#6366f1",
},
}}
>
<Typography variant="body2" sx={{ color: "#0f172a", fontWeight: 500 }}>
Generating script with AI... This may take a moment.
</Typography>
</Alert>
)}
{error && (
<Alert
severity="error"
sx={{
mb: 3,
background: "linear-gradient(135deg, rgba(239, 68, 68, 0.08) 0%, rgba(220, 38, 38, 0.08) 100%)",
border: "1px solid rgba(239, 68, 68, 0.2)",
borderRadius: 2,
boxShadow: "0 1px 2px rgba(239, 68, 68, 0.05)",
"& .MuiAlert-icon": {
color: "#ef4444",
},
}}
>
<Typography variant="body2" sx={{ color: "#0f172a", fontWeight: 500 }}>
{error}
</Typography>
</Alert>
)}
{script && (
<Stack spacing={3}>
{/* Script Format Explanation Panel */}
<Paper
sx={{
p: 3,
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.05) 0%, rgba(139, 92, 246, 0.05) 100%)",
border: "1px solid rgba(99, 102, 241, 0.15)",
borderRadius: 2,
boxShadow: "0 2px 8px rgba(99, 102, 241, 0.08)",
}}
>
<Stack direction="row" alignItems="center" justifyContent="space-between" sx={{ mb: showScriptFormatInfo ? 2 : 0 }}>
<Stack direction="row" alignItems="center" spacing={1.5}>
<Box
sx={{
width: 40,
height: 40,
borderRadius: "50%",
background: "linear-gradient(135deg, #667eea 0%, #764ba2 100%)",
display: "flex",
alignItems: "center",
justifyContent: "center",
boxShadow: "0 2px 8px rgba(102, 126, 234, 0.3)",
}}
>
<InfoIcon sx={{ color: "#ffffff", fontSize: "1.5rem" }} />
</Box>
<Box>
<Typography variant="h6" sx={{ color: "#0f172a", fontWeight: 600, fontSize: "1.1rem" }}>
Why This Script Format?
</Typography>
<Typography variant="body2" sx={{ color: "#64748b", mt: 0.25 }}>
Understanding how your script creates natural, human-like audio
</Typography>
</Box>
</Stack>
<IconButton
onClick={() => setShowScriptFormatInfo(!showScriptFormatInfo)}
sx={{
color: "#6366f1",
"&:hover": {
background: "rgba(99, 102, 241, 0.1)",
},
}}
>
{showScriptFormatInfo ? <ExpandLessIcon /> : <ExpandMoreIcon />}
</IconButton>
</Stack>
<Collapse in={showScriptFormatInfo}>
<Stack spacing={2.5}>
<Box>
<Typography variant="body2" sx={{ color: "#0f172a", lineHeight: 1.8, mb: 2 }}>
Our AI script generator creates scripts specifically optimized for <strong style={{ fontWeight: 600 }}>high-quality text-to-speech</strong>.
The format you see here is designed to produce audio that sounds natural and human-like, not robotic.
</Typography>
</Box>
<Stack spacing={2}>
<Box sx={{ display: "flex", gap: 2 }}>
<Box
sx={{
minWidth: 32,
height: 32,
borderRadius: "8px",
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.1) 0%, rgba(139, 92, 246, 0.1) 100%)",
display: "flex",
alignItems: "center",
justifyContent: "center",
flexShrink: 0,
}}
>
<Typography variant="body2" sx={{ color: "#6366f1", fontWeight: 700 }}>
1
</Typography>
</Box>
<Box>
<Typography variant="subtitle2" sx={{ color: "#0f172a", fontWeight: 600, mb: 0.5 }}>
Natural Pauses & Rhythm
</Typography>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.7 }}>
The script includes strategic pauses between lines and when speakers change. This creates natural breathing patterns
and conversation flow, just like real human speech. Without these pauses, the audio would sound rushed and robotic.
</Typography>
</Box>
</Box>
<Box sx={{ display: "flex", gap: 2 }}>
<Box
sx={{
minWidth: 32,
height: 32,
borderRadius: "8px",
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.1) 0%, rgba(139, 92, 246, 0.1) 100%)",
display: "flex",
alignItems: "center",
justifyContent: "center",
flexShrink: 0,
}}
>
<Typography variant="body2" sx={{ color: "#6366f1", fontWeight: 700 }}>
2
</Typography>
</Box>
<Box>
<Typography variant="subtitle2" sx={{ color: "#0f172a", fontWeight: 600, mb: 0.5 }}>
Emphasis Markers
</Typography>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.7 }}>
Lines marked with emphasis help highlight important points, statistics, or key insights. The AI voice will naturally
stress these parts, making your podcast more engaging and easier to followjust like a real host would emphasize important information.
</Typography>
</Box>
</Box>
<Box sx={{ display: "flex", gap: 2 }}>
<Box
sx={{
minWidth: 32,
height: 32,
borderRadius: "8px",
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.1) 0%, rgba(139, 92, 246, 0.1) 100%)",
display: "flex",
alignItems: "center",
justifyContent: "center",
flexShrink: 0,
}}
>
<Typography variant="body2" sx={{ color: "#6366f1", fontWeight: 700 }}>
3
</Typography>
</Box>
<Box>
<Typography variant="subtitle2" sx={{ color: "#0f172a", fontWeight: 600, mb: 0.5 }}>
Short, Conversational Sentences
</Typography>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.7 }}>
The script uses shorter sentences (15-20 words) written in a conversational style. This matches how people actually
speak, making the audio sound more natural. Long, complex sentences would sound awkward when spoken aloud.
</Typography>
</Box>
</Box>
<Box sx={{ display: "flex", gap: 2 }}>
<Box
sx={{
minWidth: 32,
height: 32,
borderRadius: "8px",
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.1) 0%, rgba(139, 92, 246, 0.1) 100%)",
display: "flex",
alignItems: "center",
justifyContent: "center",
flexShrink: 0,
}}
>
<Typography variant="body2" sx={{ color: "#6366f1", fontWeight: 700 }}>
4
</Typography>
</Box>
<Box>
<Typography variant="subtitle2" sx={{ color: "#0f172a", fontWeight: 600, mb: 0.5 }}>
Scene-Specific Emotions
</Typography>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.7 }}>
Each scene has an emotional tone (excited, serious, curious, etc.) that guides the AI voice's delivery. This creates
variety and keeps listeners engaged, just like a real podcast host would vary their tone based on the topic.
</Typography>
</Box>
</Box>
<Box sx={{ display: "flex", gap: 2 }}>
<Box
sx={{
minWidth: 32,
height: 32,
borderRadius: "8px",
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.1) 0%, rgba(139, 92, 246, 0.1) 100%)",
display: "flex",
alignItems: "center",
justifyContent: "center",
flexShrink: 0,
}}
>
<Typography variant="body2" sx={{ color: "#6366f1", fontWeight: 700 }}>
5
</Typography>
</Box>
<Box>
<Typography variant="subtitle2" sx={{ color: "#0f172a", fontWeight: 600, mb: 0.5 }}>
Optimized for Podcast Narration
</Typography>
<Typography variant="body2" sx={{ color: "#475569", lineHeight: 1.7 }}>
The script is optimized with slightly slower pacing and natural pronunciation settings specifically for podcast narration.
This ensures clarity and makes the content easy to understand, even when listeners are multitasking.
</Typography>
</Box>
</Box>
</Stack>
<Alert
severity="info"
sx={{
mt: 1,
background: "rgba(99, 102, 241, 0.06)",
border: "1px solid rgba(99, 102, 241, 0.15)",
"& .MuiAlert-icon": {
color: "#6366f1",
},
}}
>
<Typography variant="body2" sx={{ color: "#0f172a", lineHeight: 1.7 }}>
<strong style={{ fontWeight: 600 }}>Tip:</strong> You can edit any line or scene to match your preferences.
The format will be preserved when rendering, ensuring your audio still sounds natural and professional.
</Typography>
</Alert>
</Stack>
</Collapse>
</Paper>
<Alert
severity="info"
sx={{
background: "linear-gradient(135deg, rgba(99, 102, 241, 0.08) 0%, rgba(139, 92, 246, 0.08) 100%)",
border: "1px solid rgba(99, 102, 241, 0.2)",
borderRadius: 2,
boxShadow: "0 1px 2px rgba(99, 102, 241, 0.05)",
"& .MuiAlert-icon": {
color: "#6366f1",
},
}}
>
<Typography variant="body2" sx={{ color: "#0f172a", fontWeight: 500, lineHeight: 1.6 }}>
<strong style={{ fontWeight: 600 }}>Approval Required:</strong> Each scene must be approved before rendering. Review and edit lines as needed, then approve each scene.
</Typography>
</Alert>
<Stack spacing={2}>
{script.scenes.map((scene, idx) => (
<GlassyCard
key={scene.id}
initial={{ opacity: 0, y: 8 }}
animate={{ opacity: 1, y: 0 }}
transition={{ duration: 0.3, delay: idx * 0.1 }}
>
<SceneEditor
scene={scene}
onUpdateScene={updateScene}
onApprove={approveScene}
onDelete={deleteScene}
knobs={knobs}
approvingSceneId={approvingSceneId}
generatingAudioId={generatingAudioId}
totalScenes={script.scenes.length}
onAudioGenerationStart={(sceneId) => {
setGeneratingAudioId(sceneId);
}}
onAudioGenerated={async (sceneId, audioUrl) => {
setGeneratingAudioId(null);
// Use functional update to ensure we're working with latest state
// Ensure scene is marked as approved and has audioUrl
setScript((currentScript) => {
if (!currentScript) return currentScript;
const updatedScenes = currentScript.scenes.map((s) =>
s.id === sceneId ? { ...s, audioUrl, approved: true } : s
);
const updatedScript = { ...currentScript, scenes: updatedScenes };
emitScriptChange(updatedScript);
return updatedScript;
});
}}
idea={idea}
avatarUrl={avatarUrl}
/>
</GlassyCard>
))}
</Stack>
<Paper
sx={{
p: 3.5,
background: allApproved
? "linear-gradient(135deg, rgba(16, 185, 129, 0.05) 0%, rgba(5, 150, 105, 0.05) 100%)"
: "#ffffff",
border: allApproved
? "2px solid rgba(16, 185, 129, 0.25)"
: "1px solid rgba(15, 23, 42, 0.08)",
borderRadius: 3,
boxShadow: allApproved
? "0 4px 6px rgba(16, 185, 129, 0.08), 0 8px 24px rgba(16, 185, 129, 0.06)"
: "0 1px 3px rgba(15, 23, 42, 0.06), 0 4px 12px rgba(15, 23, 42, 0.04)",
transition: "all 0.3s cubic-bezier(0.4, 0, 0.2, 1)",
}}
>
<Stack direction="row" justifyContent="space-between" alignItems="center">
<Box>
<Typography variant="subtitle1" sx={{ mb: 1, display: "flex", alignItems: "center", gap: 1.5, color: "#0f172a", fontWeight: 600, fontSize: "1.1rem" }}>
<CheckCircleIcon fontSize="small" sx={{ color: allApproved ? "#10b981" : "#94a3b8", fontSize: "1.25rem" }} />
Approval Status
</Typography>
<Typography variant="body2" sx={{ color: "#64748b", fontWeight: 400, lineHeight: 1.6 }}>
{approvedCount} of {totalScenes} scenes approved
{allScenesHaveAudioAndImages && " • All scenes ready for video rendering"}
{!allScenesHaveAudioAndImages && allApproved && " • Generate images for all scenes to enable video rendering"}
{!allApproved && " — Approve all scenes first"}
</Typography>
{!allScenesHaveAudioAndImages && (
<LinearProgress
variant="determinate"
value={
allScenesHaveAudioAndImages
? 100
: script
? (script.scenes.filter((s) => s.audioUrl && s.imageUrl).length / totalScenes) * 100
: 0
}
sx={{ mt: 1, height: 6, borderRadius: 3 }}
/>
)}
</Box>
<PrimaryButton
onClick={() => script && onProceedToRendering(script)}
disabled={!allScenesHaveAudioAndImages}
startIcon={<PlayArrowIcon />}
tooltip={
!allScenesHaveAudioAndImages
? "Generate audio and images for all scenes to proceed to video rendering"
: "Proceed to video rendering (all scenes have audio and images)"
}
>
Proceed to Rendering
</PrimaryButton>
</Stack>
</Paper>
{/* Download Audio-Only Podcast Section */}
{allScenesHaveAudio && (
<Paper
sx={{
p: 3,
background: "linear-gradient(135deg, rgba(102, 126, 234, 0.05) 0%, rgba(118, 75, 162, 0.05) 100%)",
border: "1px solid rgba(102, 126, 234, 0.15)",
borderRadius: 2,
}}
>
<Stack spacing={3}>
<Typography variant="h6" sx={{ color: "#0f172a", fontWeight: 600 }}>
Download Audio-Only Podcast
</Typography>
{!combinedAudioResult ? (
<>
<PrimaryButton
onClick={combineAudio}
disabled={combiningAudio}
loading={combiningAudio}
startIcon={<DownloadIcon />}
tooltip="Combine all scene audio files into a single podcast episode"
sx={{
minWidth: 280,
fontSize: "1rem",
py: 1.5,
background: "linear-gradient(135deg, #667eea 0%, #764ba2 100%)",
"&:hover": {
background: "linear-gradient(135deg, #764ba2 0%, #667eea 100%)",
},
}}
>
{combiningAudio ? "Combining Audio..." : "Download Audio-Only Podcast"}
</PrimaryButton>
<Typography variant="caption" sx={{ color: "#64748b", fontStyle: "italic" }}>
This will combine all {scenesWithAudio} scene audio files into one complete podcast episode.
</Typography>
</>
) : (
<Stack spacing={2}>
{/* Success Alert */}
<Alert
severity="success"
sx={{
background: alpha("#10b981", 0.1),
border: "1px solid rgba(16,185,129,0.3)",
"& .MuiAlert-icon": { color: "#10b981" },
}}
>
<Typography variant="body2" sx={{ color: "#059669", fontWeight: 500 }}>
Combined audio generated successfully! ({combinedAudioResult.sceneCount} scenes,{" "}
{Math.round(combinedAudioResult.duration)}s)
</Typography>
</Alert>
{/* Combined Audio Preview */}
<InlineAudioPlayer audioUrl={combinedAudioResult.url} title="Complete Podcast Episode" />
{/* Action Buttons */}
<Stack direction="row" spacing={2}>
<SecondaryButton
onClick={async () => {
try {
// Normalize path
let audioPath = combinedAudioResult.url.startsWith('/')
? combinedAudioResult.url
: `/${combinedAudioResult.url}`;
// Ensure it's a podcast audio endpoint
if (!audioPath.includes('/api/podcast/audio/')) {
const filename = audioPath.split('/').pop() || combinedAudioResult.filename;
audioPath = `/api/podcast/audio/${filename}`;
}
// Remove query parameters if present
audioPath = audioPath.split('?')[0];
// Fetch as blob using authenticated client
const response = await aiApiClient.get(audioPath, {
responseType: 'blob',
});
// Create blob URL and download
const blob = response.data;
const blobUrl = URL.createObjectURL(blob);
const link = document.createElement("a");
link.href = blobUrl;
link.download = combinedAudioResult.filename || `podcast-episode-${projectId.slice(-8)}.mp3`;
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
// Clean up blob URL after a delay
setTimeout(() => {
URL.revokeObjectURL(blobUrl);
}, 100);
} catch (error) {
console.error('Failed to download audio:', error);
onError('Failed to download audio file. Please try again.');
}
}}
startIcon={<DownloadIcon />}
tooltip="Download the combined audio file again"
>
Download Again
</SecondaryButton>
<SecondaryButton
onClick={() => {
setCombinedAudioResult(null);
combineAudio();
}}
disabled={combiningAudio}
loading={combiningAudio}
startIcon={<RefreshIcon />}
tooltip="Regenerate combined audio (useful if scenes were updated)"
>
Regenerate
</SecondaryButton>
</Stack>
</Stack>
)}
</Stack>
</Paper>
)}
</Stack>
)}
</Box>
);
};

334
_session_backup/analysis.py Normal file
View File

@@ -0,0 +1,334 @@
"""
Podcast Analysis Handlers
Analysis endpoint for podcast ideas.
"""
from fastapi import APIRouter, Depends, HTTPException
from typing import Dict, Any
import json
import uuid
from sqlalchemy.orm import Session
from services.database import get_db
from middleware.auth_middleware import get_current_user
from api.story_writer.utils.auth import require_authenticated_user
from services.llm_providers.main_text_generation import llm_text_gen
from services.llm_providers.main_image_generation import generate_image
from services.podcast_bible_service import PodcastBibleService
from utils.asset_tracker import save_asset_to_library
from loguru import logger
from ..constants import PODCAST_IMAGES_DIR
from ..models import (
PodcastAnalyzeRequest,
PodcastAnalyzeResponse,
PodcastEnhanceIdeaRequest,
PodcastEnhanceIdeaResponse
)
router = APIRouter()
@router.post("/idea/enhance", response_model=PodcastEnhanceIdeaResponse)
async def enhance_podcast_idea(
request: PodcastEnhanceIdeaRequest,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""
Take raw keywords/topic and use AI to craft a presentable, detailed podcast idea.
Uses the user's Podcast Bible for hyper-personalization if available.
"""
user_id = require_authenticated_user(current_user)
# Serialize Bible context if provided or generate from onboarding
bible_context = ""
try:
bible_service = PodcastBibleService()
if request.bible:
from models.podcast_bible_models import PodcastBible
bible_data = PodcastBible(**request.bible)
bible_context = bible_service.serialize_bible(bible_data)
else:
# Generate from onboarding data directly
bible_obj = bible_service.generate_bible(user_id, "temp_enhance")
bible_context = bible_service.serialize_bible(bible_obj)
except Exception as exc:
logger.warning(f"[Podcast Enhance] Failed to parse or generate bible context: {exc}")
prompt = f"""
You are a creative podcast producer. Generate 3 distinct, compelling podcast episode concepts from the raw idea.
{f"USER PERSONALIZATION CONTEXT (Podcast Bible):\n{bible_context}\n" if bible_context else ""}
RAW IDEA/KEYWORDS: "{request.idea}"
TASK:
Generate 3 different enhanced versions, each with a unique angle:
1. Professional & Expert-led angle (focus on authority, insights, and expertise)
2. Storytelling & Human interest angle (focus on narratives, emotions, and personal connections)
3. Trendy & Contemporary angle (focus on current trends, modern perspectives, and relevance)
Each version should be 2-3 sentences, audience-focused, and align with host persona if provided.
Return JSON with:
- enhanced_ideas: array of 3 enhanced episode pitches (in order: Professional, Storytelling, Trendy)
- rationales: array of 3 rationales explaining the approach for each version
"""
try:
raw = llm_text_gen(
prompt=prompt,
user_id=user_id,
json_struct=None,
preferred_provider="huggingface",
flow_type="premium_tool",
)
# Normalize response
if isinstance(raw, str):
data = json.loads(raw)
else:
data = raw
# Extract enhanced ideas and rationales with fallbacks
enhanced_ideas = data.get("enhanced_ideas", [])
rationales = data.get("rationales", [])
# Ensure we have exactly 3 ideas, fallback to original if needed
if not isinstance(enhanced_ideas, list) or len(enhanced_ideas) != 3:
# Fallback: create 3 variations of the original idea
base_idea = request.idea
enhanced_ideas = [
f"Expert insights on {base_idea}: A deep dive into industry trends and best practices.",
f"The human side of {base_idea}: Personal stories and real-world experiences that resonate.",
f"Modern perspectives on {base_idea}: Current trends and forward-thinking approaches."
]
rationales = [
"Professional approach focusing on expertise and authority",
"Storytelling approach emphasizing human connection",
"Contemporary approach highlighting current relevance"
]
# Ensure rationales match the number of ideas
if not isinstance(rationales, list) or len(rationales) != 3:
rationales = [
"Professional angle with expert insights",
"Storytelling angle with human interest",
"Trendy angle with contemporary relevance"
]
return PodcastEnhanceIdeaResponse(
enhanced_ideas=enhanced_ideas[:3], # Ensure exactly 3
rationales=rationales[:3] # Ensure exactly 3
)
except Exception as exc:
logger.error(f"[Podcast Enhance] Failed for user {user_id}: {exc}")
# Fallback to basic variations of original idea
base_idea = request.idea
return PodcastEnhanceIdeaResponse(
enhanced_ideas=[
f"Expert insights on {base_idea}: A deep dive into industry trends and best practices.",
f"The human side of {base_idea}: Personal stories and real-world experiences that resonate.",
f"Modern perspectives on {base_idea}: Current trends and forward-thinking approaches."
],
rationales=[
"Professional approach focusing on expertise and authority",
"Storytelling approach emphasizing human connection",
"Contemporary approach highlighting current relevance"
]
)
@router.post("/analyze", response_model=PodcastAnalyzeResponse)
async def analyze_podcast_idea(
request: PodcastAnalyzeRequest,
current_user: Dict[str, Any] = Depends(get_current_user),
db: Session = Depends(get_db),
):
"""
Analyze a podcast idea and return podcast-oriented outlines, keywords, and titles.
If no avatar_url is provided, it generates one automatically based on the host's look.
"""
user_id = require_authenticated_user(current_user)
# Serialize Bible context if provided or generate from onboarding
bible_context = ""
bible_obj = None
try:
bible_service = PodcastBibleService()
if request.bible:
from models.podcast_bible_models import PodcastBible
bible_data = PodcastBible(**request.bible)
bible_context = bible_service.serialize_bible(bible_data)
bible_obj = bible_data
else:
# Generate from onboarding data directly
bible_obj = bible_service.generate_bible(user_id, "temp_analyze")
bible_context = bible_service.serialize_bible(bible_obj)
bible_obj = bible_obj
except Exception as exc:
logger.warning(f"[Podcast Analyze] Failed to parse or generate bible context: {exc}")
# --- NEW: Generate Presenter Avatar if missing ---
final_avatar_url = request.avatar_url
final_avatar_prompt = None
if not final_avatar_url:
logger.info(f"[Podcast Analyze] No avatar_url provided, generating one for user {user_id}")
try:
# 1. PRE-FLIGHT VALIDATION: Check subscription limits for image generation
from services.subscription import PricingService
from services.subscription.preflight_validator import validate_image_generation_operations
pricing_service = PricingService(db)
validate_image_generation_operations(
pricing_service=pricing_service,
user_id=user_id,
num_images=1
)
# 2. Build avatar prompt from Bible host look or fallback
host_look = bible_obj.host.look if bible_obj and bible_obj.host.look else "A professional podcast host"
visual_style = bible_obj.visual_style.style_preset if bible_obj else "Realistic Photography"
final_avatar_prompt = f"Professional headshot of a podcast host, {host_look}, {visual_style} style, clean background, soft studio lighting, center-focused, high resolution, sharp focus, professional photography quality, 16:9 aspect ratio."
# 3. Generate the image
logger.info(f"[Podcast Analyze] Generating avatar with prompt: {final_avatar_prompt}")
image_result = generate_image(
prompt=final_avatar_prompt,
user_id=user_id,
width=1024,
height=1024
)
# 4. Save to disk and library
if image_result and image_result.image_bytes:
img_id = str(uuid.uuid4())[:8]
filename = f"presenter_podcast_{user_id}_{img_id}.png"
output_path = PODCAST_IMAGES_DIR / filename
PODCAST_IMAGES_DIR.mkdir(parents=True, exist_ok=True)
with open(output_path, "wb") as f:
f.write(image_result.image_bytes)
final_avatar_url = f"/api/podcast/images/avatars/{filename}"
# Save to asset library for reuse
save_asset_to_library(
db=db,
user_id=user_id,
asset_type="image",
file_url=final_avatar_url,
filename=filename,
title=f"Presenter Avatar - {request.idea[:40]}",
description=f"AI-generated podcast presenter for: {request.idea}",
provider=image_result.provider,
model=image_result.model,
cost=image_result.cost
)
logger.info(f"[Podcast Analyze] ✅ Generated and saved avatar to {final_avatar_url}")
except Exception as e:
logger.error(f"[Podcast Analyze] ❌ Failed to generate avatar: {e}")
# Non-fatal: continue analysis even if avatar generation fails
# --- END: Avatar Generation ---
# Incorporate user feedback if provided
feedback_context = ""
if request.feedback:
feedback_context = f"""
USER REGENERATION FEEDBACK:
The user was not satisfied with the previous analysis. They provided the following instructions for improvement:
"{request.feedback}"
Please prioritize this feedback and adjust the analysis accordingly.
"""
prompt = f"""
You are an expert podcast producer and research strategist. Given a podcast idea, craft concise podcast-ready assets
that sound like episode plans (not fiction stories).
{f"USER PERSONALIZATION CONTEXT (Podcast Bible):\n{bible_context}\n" if bible_context else ""}
{feedback_context}
Podcast Idea: "{request.idea}"
Duration: ~{request.duration} minutes
Speakers: {request.speakers} (host + optional guest)
TASK:
1. Define the target audience and content type aligned with the Bible's "Audience DNA" and "Brand DNA".
2. Identify 5 high-impact keywords.
3. Propose 2 episode outlines with factual segments.
4. Suggest 3 titles.
5. IMPORTANT: Generate 4-6 specific research queries for Exa. These queries MUST be highly targeted to the episode's topic, the host's expertise level, and the audience's interests as defined in the Bible.
* Do NOT use generic queries like "latest trends in X".
* DO use queries that look for case studies, specific data points, expert opinions, or contrasting viewpoints that would make for a deep, insightful podcast conversation.
Return JSON with:
- audience: short target audience description
- content_type: podcast style/format
- top_keywords: 5 podcast-relevant keywords/phrases
- suggested_outlines: 2 items, each with title (<=60 chars) and 4-6 short segments (bullet-friendly, factual)
- title_suggestions: 3 concise episode titles
- research_queries: array of {{"query": "string", "rationale": "string"}}
- exa_suggested_config: suggested Exa search options with:
- exa_search_type: "auto" | "neural" | "keyword"
- exa_category: one of ["research paper","news","company","github","tweet","personal site","pdf","financial report","linkedin profile"]
- exa_include_domains: up to 3 reputable domains
- exa_exclude_domains: up to 3 domains
- max_sources: 6-10
- include_statistics: boolean
- date_range: one of ["last_month","last_3_months","last_year","all_time"]
Requirements:
- Keep language factual, actionable, and suited for spoken audio.
- Avoid narrative fiction tone.
- Prefer 2024-2025 context.
"""
try:
raw = llm_text_gen(
prompt=prompt,
user_id=user_id,
json_struct=None,
preferred_provider="huggingface",
flow_type="premium_tool",
)
except HTTPException:
# Re-raise HTTPExceptions (e.g., 429 subscription limit) - preserve error details
raise
except Exception as exc:
logger.error(f"[Podcast Analyze] Analysis failed for user {user_id}: {exc}")
raise HTTPException(status_code=500, detail=f"Analysis failed: {exc}")
# Normalize response (accept dict or JSON string)
if isinstance(raw, str):
try:
data = json.loads(raw)
except json.JSONDecodeError:
raise HTTPException(status_code=500, detail="LLM returned non-JSON output")
elif isinstance(raw, dict):
data = raw
else:
raise HTTPException(status_code=500, detail="Unexpected LLM response format")
audience = data.get("audience") or "Growth-focused professionals"
content_type = data.get("content_type") or "Interview + insights"
top_keywords = data.get("top_keywords") or []
suggested_outlines = data.get("suggested_outlines") or []
title_suggestions = data.get("title_suggestions") or []
research_queries = data.get("research_queries") or []
exa_suggested_config = data.get("exa_suggested_config") or None
return PodcastAnalyzeResponse(
audience=audience,
content_type=content_type,
top_keywords=top_keywords,
suggested_outlines=suggested_outlines,
title_suggestions=title_suggestions,
research_queries=research_queries,
exa_suggested_config=exa_suggested_config,
bible=bible_obj.model_dump() if bible_obj else None,
avatar_url=final_avatar_url,
avatar_prompt=final_avatar_prompt,
)

422
_session_backup/models.py Normal file
View File

@@ -0,0 +1,422 @@
"""
Podcast API Models
All Pydantic request/response models for podcast endpoints.
"""
from pydantic import BaseModel, Field, model_validator
from typing import List, Optional, Dict, Any
from datetime import datetime
from enum import Enum
class PodcastProjectResponse(BaseModel):
"""Response model for podcast project."""
id: int
project_id: str
user_id: str
idea: str
duration: int
speakers: int
budget_cap: float
analysis: Optional[Dict[str, Any]] = None
queries: Optional[List[Dict[str, Any]]] = None
selected_queries: Optional[List[str]] = None
research: Optional[Dict[str, Any]] = None
raw_research: Optional[Dict[str, Any]] = None
estimate: Optional[Dict[str, Any]] = None
script_data: Optional[Dict[str, Any]] = None
bible: Optional[Dict[str, Any]] = None
render_jobs: Optional[List[Dict[str, Any]]] = None
knobs: Optional[Dict[str, Any]] = None
research_provider: Optional[str] = None
show_script_editor: bool = False
show_render_queue: bool = False
current_step: Optional[str] = None
status: str = "draft"
is_favorite: bool = False
final_video_url: Optional[str] = None
avatar_url: Optional[str] = None
avatar_prompt: Optional[str] = None
avatar_persona_id: Optional[str] = None
created_at: datetime
updated_at: datetime
class Config:
from_attributes = True
class PodcastAnalyzeRequest(BaseModel):
"""Request model for podcast idea analysis."""
idea: str = Field(..., description="Podcast topic or idea")
duration: int = Field(default=10, description="Target duration in minutes")
speakers: int = Field(default=1, description="Number of speakers")
bible: Optional[Dict[str, Any]] = Field(None, description="Optional Podcast Bible for context")
avatar_url: Optional[str] = Field(None, description="Current avatar URL if selected")
feedback: Optional[str] = Field(None, description="User feedback for regeneration")
class PodcastAnalyzeResponse(BaseModel):
"""Response model for podcast idea analysis."""
audience: str
content_type: str
top_keywords: list[str]
suggested_outlines: list[Dict[str, Any]]
title_suggestions: list[str]
research_queries: Optional[List[Dict[str, str]]] = None
exa_suggested_config: Optional[Dict[str, Any]] = None
bible: Optional[Dict[str, Any]] = None
avatar_url: Optional[str] = None
avatar_prompt: Optional[str] = None
class PodcastEnhanceIdeaRequest(BaseModel):
"""Request model for enhancing a podcast idea with AI."""
idea: str = Field(..., description="The raw podcast idea or keywords")
bible: Optional[Dict[str, Any]] = Field(None, description="Optional Podcast Bible for context")
class PodcastEnhanceIdeaResponse(BaseModel):
"""Response model for enhanced podcast idea."""
enhanced_ideas: List[str] = Field(..., description="3 AI-enhanced topic choices")
rationales: List[str] = Field(..., description="Rationale for each enhanced idea")
class PodcastScriptRequest(BaseModel):
"""Request model for podcast script generation."""
idea: str = Field(..., description="Podcast idea or topic")
duration_minutes: int = Field(default=10, description="Target duration in minutes")
speakers: int = Field(default=1, description="Number of speakers")
research: Optional[Dict[str, Any]] = Field(None, description="Optional research payload to ground the script")
bible: Optional[Dict[str, Any]] = Field(None, description="Podcast Bible for hyper-personalization")
outline: Optional[Dict[str, Any]] = Field(None, description="The refined episode outline to follow")
analysis: Optional[Dict[str, Any]] = Field(None, description="The full analysis context (audience, keywords, etc.)")
class PodcastSceneLine(BaseModel):
speaker: str
text: str
emphasis: Optional[bool] = False
class PodcastScene(BaseModel):
id: str
title: str
duration: int
lines: list[PodcastSceneLine]
approved: bool = False
emotion: Optional[str] = None
imageUrl: Optional[str] = None # Generated image URL for video generation
class PodcastExaConfig(BaseModel):
"""Exa config for podcast research."""
exa_search_type: Optional[str] = Field(default="auto", description="auto | keyword | neural")
exa_category: Optional[str] = None
exa_include_domains: List[str] = []
exa_exclude_domains: List[str] = []
max_sources: int = 8
include_statistics: Optional[bool] = False
date_range: Optional[str] = Field(default=None, description="last_month | last_3_months | last_year | all_time")
@model_validator(mode="after")
def validate_domains(self):
if self.exa_include_domains and self.exa_exclude_domains:
# Exa API does not allow both include and exclude domains together with contents
# Prefer include_domains and drop exclude_domains
self.exa_exclude_domains = []
return self
class PodcastExaResearchRequest(BaseModel):
"""Request for podcast research using Exa directly (no blog writer)."""
topic: str
queries: List[str]
exa_config: Optional[PodcastExaConfig] = None
bible: Optional[Dict[str, Any]] = Field(None, description="Podcast Bible for hyper-personalization")
analysis: Optional[Dict[str, Any]] = Field(None, description="Podcast analysis context (audience, content type, etc.)")
class PodcastExaSource(BaseModel):
title: str = ""
url: str = ""
excerpt: str = ""
published_at: Optional[str] = None
highlights: Optional[List[str]] = None
summary: Optional[str] = None
source_type: Optional[str] = None
index: Optional[int] = None
image: Optional[str] = None
author: Optional[str] = None
class PodcastResearchInsight(BaseModel):
"""Deep insight extracted from research."""
title: str
content: str
source_indices: List[int] = []
class PodcastExaResearchResponse(BaseModel):
sources: List[PodcastExaSource]
search_queries: List[str] = []
summary: str = ""
key_insights: List[PodcastResearchInsight] = []
expert_quotes: List[Dict[str, Any]] = []
listener_cta: List[str] = []
mapped_angles: List[Dict[str, Any]] = []
cost: Optional[Dict[str, Any]] = None
search_type: Optional[str] = None
provider: str = "exa"
content: Optional[str] = None # Raw aggregated content (deprecated)
class PodcastScriptResponse(BaseModel):
scenes: list[PodcastScene]
class PodcastAudioRequest(BaseModel):
"""Generate TTS for a podcast scene."""
scene_id: str
scene_title: str
text: str
voice_id: Optional[str] = "Wise_Woman"
speed: Optional[float] = 1.0
volume: Optional[float] = 1.0
pitch: Optional[float] = 0.0
emotion: Optional[str] = "neutral"
english_normalization: Optional[bool] = False # Better number reading for statistics
sample_rate: Optional[int] = None
bitrate: Optional[int] = None
channel: Optional[str] = None
format: Optional[str] = None
language_boost: Optional[str] = None
enable_sync_mode: Optional[bool] = True
class PodcastAudioResponse(BaseModel):
scene_id: str
scene_title: str
audio_filename: str
audio_url: str
provider: str
model: str
voice_id: str
text_length: int
file_size: int
cost: float
class PodcastProjectListResponse(BaseModel):
"""Response model for project list."""
projects: List[PodcastProjectResponse]
total: int
limit: int
offset: int
class CreateProjectRequest(BaseModel):
"""Request model for creating a project."""
project_id: str = Field(..., description="Unique project ID")
idea: str = Field(..., description="Episode idea or URL")
duration: int = Field(..., description="Duration in minutes")
speakers: int = Field(default=1, description="Number of speakers")
budget_cap: float = Field(default=50.0, description="Budget cap in USD")
avatar_url: Optional[str] = Field(None, description="Optional presenter avatar URL")
class UpdateProjectRequest(BaseModel):
"""Request model for updating project state."""
analysis: Optional[Dict[str, Any]] = None
queries: Optional[List[Dict[str, Any]]] = None
selected_queries: Optional[List[str]] = None
research: Optional[Dict[str, Any]] = None
raw_research: Optional[Dict[str, Any]] = None
estimate: Optional[Dict[str, Any]] = None
script_data: Optional[Dict[str, Any]] = None
bible: Optional[Dict[str, Any]] = None
render_jobs: Optional[List[Dict[str, Any]]] = None
knobs: Optional[Dict[str, Any]] = None
research_provider: Optional[str] = None
show_script_editor: Optional[bool] = None
show_render_queue: Optional[bool] = None
current_step: Optional[str] = None
status: Optional[str] = None
final_video_url: Optional[str] = None
class PodcastCombineAudioRequest(BaseModel):
"""Request model for combining podcast audio files."""
project_id: str
scene_ids: List[str] = Field(..., description="List of scene IDs to combine")
scene_audio_urls: List[str] = Field(..., description="List of audio URLs for each scene")
class PodcastCombineAudioResponse(BaseModel):
"""Response model for combined podcast audio."""
combined_audio_url: str
combined_audio_filename: str
total_duration: float
file_size: int
scene_count: int
class PodcastImageRequest(BaseModel):
"""Request for generating an image for a podcast scene."""
scene_id: str
scene_title: str
scene_content: Optional[str] = None # Optional: scene lines text for context
idea: Optional[str] = None # Optional: podcast idea for context
base_avatar_url: Optional[str] = None # Base avatar image URL for scene variations
bible: Optional[Dict[str, Any]] = Field(None, description="Podcast Bible for hyper-personalization")
width: int = 1024
height: int = 1024
custom_prompt: Optional[str] = None # Custom prompt from user (overrides auto-generated prompt)
style: Optional[str] = None # "Auto", "Fiction", or "Realistic"
rendering_speed: Optional[str] = None # "Default", "Turbo", or "Quality"
aspect_ratio: Optional[str] = None # "1:1", "16:9", "9:16", "4:3", "3:4"
class PodcastImageResponse(BaseModel):
"""Response for podcast scene image generation."""
scene_id: str
scene_title: str
image_filename: str
image_url: str
width: int
height: int
provider: str
model: Optional[str] = None
cost: float
class PodcastVideoGenerationRequest(BaseModel):
"""Request model for podcast video generation."""
project_id: str = Field(..., description="Podcast project ID")
scene_id: str = Field(..., description="Scene ID")
scene_title: str = Field(..., description="Scene title")
audio_url: str = Field(..., description="URL to the generated audio file")
avatar_image_url: Optional[str] = Field(None, description="URL to scene image (required for video generation)")
bible: Optional[Dict[str, Any]] = Field(None, description="Podcast Bible for hyper-personalization")
resolution: str = Field("720p", description="Video resolution (480p or 720p)")
prompt: Optional[str] = Field(None, description="Optional animation prompt override")
seed: Optional[int] = Field(-1, description="Random seed; -1 for random")
mask_image_url: Optional[str] = Field(None, description="Optional mask image URL to specify animated region")
class PodcastVideoGenerationResponse(BaseModel):
"""Response model for podcast video generation."""
task_id: str
status: str
message: str
class PodcastCombineVideosRequest(BaseModel):
"""Request to combine scene videos into final podcast"""
project_id: str = Field(..., description="Project ID")
scene_video_urls: list[str] = Field(..., description="List of scene video URLs in order")
podcast_title: str = Field(default="Podcast", description="Title for the final podcast video")
class PodcastCombineVideosResponse(BaseModel):
"""Response from combine videos endpoint"""
task_id: str
status: str
message: str
class AudioDubbingQuality(str, Enum):
LOW = "low"
HIGH = "high"
@classmethod
def from_string(cls, value: str) -> "AudioDubbingQuality":
if value.lower() == "high":
return cls.HIGH
return cls.LOW
class PodcastAudioDubRequest(BaseModel):
"""Request model for audio dubbing."""
source_audio_url: str = Field(..., description="URL or path to source audio file")
source_language: Optional[str] = Field(None, description="Source language code (auto-detected if None)")
target_language: str = Field(..., description="Target language for dubbing")
quality: str = Field(default="low", description="Translation quality: low (DeepL) or high (WaveSpeed)")
voice_id: Optional[str] = Field(default="Wise_Woman", description="Voice ID for TTS")
speed: Optional[float] = Field(default=1.0, ge=0.5, le=2.0, description="Speech speed (0.5-2.0)")
emotion: Optional[str] = Field(default="happy", description="Emotion for TTS voice")
preserve_emotion: Optional[bool] = Field(default=True, description="Preserve emotional tone in translation")
use_voice_clone: Optional[bool] = Field(default=False, description="Use voice cloning to preserve original speaker's voice")
custom_voice_id: Optional[str] = Field(None, description="Custom name for the cloned voice")
voice_clone_accuracy: Optional[float] = Field(default=0.7, ge=0.1, le=1.0, description="Voice cloning accuracy (0.1-1.0)")
class PodcastAudioDubResponse(BaseModel):
"""Response model for audio dubbing task creation."""
task_id: str
status: str = "pending"
message: str = "Audio dubbing task created"
class PodcastAudioDubResult(BaseModel):
"""Response model for completed audio dubbing."""
dubbed_audio_url: str
dubbed_audio_filename: str
original_transcript: str
translated_transcript: str
source_language: str
target_language: str
voice_id: str
quality: str
duration_seconds: int
file_size: int
cost: float
task_id: str
status: str = "completed"
voice_clone_used: Optional[bool] = Field(default=False, description="Whether voice cloning was used")
cloned_voice_id: Optional[str] = Field(None, description="ID of the cloned voice if voice_clone_used=True")
class PodcastAudioDubEstimateRequest(BaseModel):
"""Request model for dubbing cost estimation."""
audio_duration_seconds: float = Field(..., description="Duration of source audio in seconds")
target_language: str = Field(..., description="Target language")
quality: str = Field(default="low", description="Translation quality")
use_voice_clone: Optional[bool] = Field(default=False, description="Include voice cloning cost")
class PodcastAudioDubEstimateResponse(BaseModel):
"""Response model for dubbing cost estimation."""
estimated_characters: int
translation_cost: float
tts_cost: float
voice_clone_cost: float = 0.0
total_cost: float
currency: str = "USD"
class VoiceCloneRequest(BaseModel):
"""Request model for voice cloning."""
source_audio_url: str = Field(..., description="URL or path to source audio file (10-60 seconds recommended)")
custom_voice_id: Optional[str] = Field(None, description="Custom name for the cloned voice")
accuracy: Optional[float] = Field(default=0.7, ge=0.1, le=1.0, description="Cloning accuracy (0.1-1.0)")
language_boost: Optional[str] = Field(None, description="Language to optimize the voice for")
class VoiceCloneResponse(BaseModel):
"""Response model for voice cloning."""
task_id: str
status: str = "pending"
message: str = "Voice cloning task created"
class VoiceCloneResult(BaseModel):
"""Response model for completed voice cloning."""
voice_id: str
voice_url: str
source_language: str
accuracy: float
file_size: int
task_id: str
status: str = "completed"

View File

@@ -0,0 +1,837 @@
import { ResearchProvider, ResearchConfig } from "./blogWriterApi";
import {
storyWriterApi,
StorySetupGenerationResponse,
} from "./storyWriterApi";
import { getResearchConfig, ResearchPersona } from "../api/researchConfig";
import { aiApiClient } from "../api/client";
import {
CreateProjectPayload,
CreateProjectResult,
Fact,
Knobs,
PodcastAnalysis,
PodcastEstimate,
Query,
RenderJobResult,
Research,
Scene,
Script,
} from "../components/PodcastMaker/types";
import { checkPreflight, PreflightOperation } from "./billingService";
import { TaskStatus } from "./storyWriterApi";
const DEFAULT_KNOBS: Knobs = {
voice_emotion: "neutral",
voice_speed: 1,
resolution: "720p",
scene_length_target: 45,
sample_rate: 24000,
bitrate: "standard",
};
// const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
const createId = (prefix: string) => {
if (typeof crypto !== "undefined" && typeof crypto.randomUUID === "function") {
return `${prefix}_${crypto.randomUUID()}`;
}
return `${prefix}_${Date.now()}_${Math.floor(Math.random() * 10000)}`;
};
type OptionLike = StorySetupGenerationResponse["options"][0] | { plot_elements?: string; premise?: string };
const deriveSegments = (option?: OptionLike): string[] => {
const segments: string[] = [];
if (option?.plot_elements) {
option.plot_elements
.split(/[,.;]+/)
.map((p) => p.trim())
.filter(Boolean)
.forEach((p) => segments.push(p));
}
if (!segments.length && "premise" in (option || {}) && (option as any)?.premise) {
segments.push("Intro", "Key Takeaways", "Examples", "CTA");
}
return segments.slice(0, 5);
};
const estimateCosts = ({
minutes,
scenes,
chars,
quality,
avatars,
queryCount = 3,
}: {
minutes: number;
scenes: number;
chars: number;
quality: string;
avatars: number;
queryCount?: number;
}): PodcastEstimate => {
const secs = Math.max(60, minutes * 60);
const ttsCost = (chars / 1000) * 0.05;
const avatarCost = avatars * 0.15;
const videoRate = quality === "hd" ? 0.06 : 0.03;
const videoCost = secs * videoRate;
const researchCost = +(Math.max(1, queryCount) * 0.1).toFixed(2);
const total = +(ttsCost + avatarCost + videoCost + researchCost).toFixed(2);
return {
ttsCost: +ttsCost.toFixed(2),
avatarCost: +avatarCost.toFixed(2),
videoCost: +videoCost.toFixed(2),
researchCost,
total,
};
};
const mapPersonaQueries = (persona: ResearchPersona | undefined, seed: string): Query[] => {
const baseIdea = seed || "AI marketing for small businesses";
const personaKeywords = persona?.suggested_keywords?.filter(Boolean) || [];
const angles = persona?.research_angles ?? [];
const generated: Query[] = [];
const addQuery = (q: string, why: string, needsRecent = false) => {
if (!q.trim()) return;
generated.push({
id: createId("q"),
query: q.trim(),
rationale: why,
needsRecentStats: needsRecent,
});
};
if (personaKeywords.length) {
personaKeywords.slice(0, 4).forEach((k, idx) =>
addQuery(k, angles[idx % Math.max(1, angles.length)] || "Persona-aligned query", /202[45]|latest|trend/i.test(k))
);
}
if (!generated.length) {
addQuery(`How is ${baseIdea} evolving in 2024?`, "Trend + outcome focus", true);
addQuery(`Best practices for ${baseIdea}`, "Actionable guidance", false);
addQuery(`${baseIdea} case studies with ROI`, "Proof and outcomes", true);
addQuery(`${baseIdea} risks and objections`, "Address listener concerns", false);
}
return generated.slice(0, 6);
};
const mapSourcesToFacts = (sources: ExaSource[]): Fact[] => {
if (!sources || !sources.length) return [];
return sources.slice(0, 12).map((source: ExaSource, idx: number) => ({
id: source.url || createId("fact"),
quote: source.excerpt || source.title || "Insight",
url: source.url || "",
date: source.published_at || "Unknown",
confidence: typeof (source as any).credibility_score === "number" ? (source as any).credibility_score : Math.max(0.5, 0.85 - idx * 0.02),
image: source.image,
author: source.author,
highlights: source.highlights,
}));
};
type ExaSource = {
title?: string;
url?: string;
excerpt?: string;
published_at?: string;
highlights?: string[];
summary?: string;
source_type?: string;
index?: number;
image?: string;
author?: string;
};
type ExaResearchResult = {
sources: ExaSource[];
search_queries?: string[];
cost?: { total?: number };
search_type?: string;
provider?: string;
content?: string;
};
const mapExaResearchResponse = (response: any): Research => {
const factCards = mapSourcesToFacts(response.sources);
// Use backend summary if available, otherwise use full content (no truncation) or fallback text
const summary = response.summary || response.content || "Research completed.";
const keyInsights = (response.key_insights || []).map((insight: any) => ({
title: insight.title || "Insight",
content: insight.content || "",
source_indices: insight.source_indices || []
}));
const expertQuotes = (response.expert_quotes || []).map((eq: any) => ({
quote: eq.quote || eq.text || "",
source_index: eq.source_index ?? 0
}));
const listenerCta = response.listener_cta || [];
const mappedAngles = (response.mapped_angles || []).map((angle: any) => ({
title: angle.title || "",
why: angle.why || angle.rationale || "",
mappedFactIds: angle.mapped_fact_ids || angle.mappedFactIds || []
}));
return {
summary,
keyInsights,
factCards,
mappedAngles,
expertQuotes,
listenerCta,
searchQueries: response.search_queries,
searchType: response.search_type,
provider: response.provider || "exa",
cost: response.cost?.total,
sourceCount: response.sources?.length || 0,
};
};
const ensurePreflight = async (operation: PreflightOperation) => {
const result = await checkPreflight(operation);
if (!result.can_proceed) {
const message = result.operations[0]?.message || "Pre-flight validation failed";
throw new Error(message);
}
return result;
};
export const podcastApi = {
async createProject(payload: CreateProjectPayload, bible?: any, feedback?: string): Promise<CreateProjectResult> {
const storyIdea = payload.ideaOrUrl || "AI marketing for small businesses";
await ensurePreflight({
provider: "gemini",
operation_type: "podcast_analysis",
tokens_requested: 1500,
actual_provider_name: "gemini",
});
// Podcast-specific analysis (not story setup)
const analysisResp = await aiApiClient.post("/api/podcast/analyze", {
idea: storyIdea,
duration: payload.duration,
speakers: payload.speakers,
bible: bible,
avatar_url: payload.avatarUrl,
feedback: feedback, // Pass feedback to backend
});
const outlines = (analysisResp.data?.suggested_outlines || []).map((o: any, idx: number) => ({
id: o.id || `outline-${idx + 1}`,
title: o.title || `Outline ${idx + 1}`,
segments: Array.isArray(o.segments) ? o.segments : deriveSegments({ plot_elements: o.segments }),
}));
const analysis: PodcastAnalysis = {
audience: analysisResp.data?.audience || "Growth-minded pros",
contentType: analysisResp.data?.content_type || "Podcast interview",
topKeywords: analysisResp.data?.top_keywords || outlines[0]?.segments?.slice(0, 3) || [],
suggestedOutlines: outlines,
suggestedKnobs: { ...DEFAULT_KNOBS, ...payload.knobs },
titleSuggestions: (analysisResp.data?.title_suggestions || []).filter(Boolean),
research_queries: analysisResp.data?.research_queries || [],
exaSuggestedConfig: analysisResp.data?.exa_suggested_config || undefined,
};
const researchConfig = await getResearchConfig().catch(() => null);
// Use AI-generated queries if available, fallback to legacy mapping
let queries: Query[] = [];
if (analysis.research_queries && analysis.research_queries.length > 0) {
queries = analysis.research_queries.map(rq => ({
id: createId("q"),
query: rq.query,
rationale: rq.rationale,
needsRecentStats: /202[45]|latest|trend/i.test(rq.query)
}));
} else {
queries = mapPersonaQueries(researchConfig?.research_persona, storyIdea);
}
const projectId = createId("podcast");
const estimate = estimateCosts({
minutes: payload.duration,
scenes: Math.ceil((payload.duration * 60) / (payload.knobs.scene_length_target || DEFAULT_KNOBS.scene_length_target)),
chars: Math.max(1000, payload.duration * 900),
quality: payload.knobs.bitrate || "standard",
avatars: payload.speakers,
queryCount: queries.length || 3,
});
return {
projectId,
analysis,
estimate,
queries,
bible: analysisResp.data?.bible || undefined,
avatar_url: analysisResp.data?.avatar_url || null,
avatar_prompt: analysisResp.data?.avatar_prompt || null,
};
},
async enhanceIdea(params: { idea: string; bible?: any }): Promise<{ enhanced_ideas: string[]; rationales: string[] }> {
const response = await aiApiClient.post("/api/podcast/idea/enhance", params);
return response.data;
},
async runResearch(params: {
projectId: string;
topic: string;
approvedQueries: Query[];
provider?: ResearchProvider;
exaConfig?: ResearchConfig;
bible?: any;
analysis?: PodcastAnalysis | null;
onProgress?: (message: string) => void;
}): Promise<{ research: Research; raw: any }> {
const keywords = params.approvedQueries.map((q) => q.query).filter(Boolean);
if (!keywords.length) {
throw new Error("At least one query must be approved for research.");
}
// Ensure Exa payload respects API constraint: when requesting contents, only one of includeDomains or excludeDomains.
let sanitizedExaConfig: ResearchConfig | undefined = params.exaConfig;
if (sanitizedExaConfig && sanitizedExaConfig.exa_include_domains?.length) {
sanitizedExaConfig = {
...sanitizedExaConfig,
exa_exclude_domains: undefined,
};
} else if (sanitizedExaConfig && sanitizedExaConfig.exa_exclude_domains?.length) {
sanitizedExaConfig = {
...sanitizedExaConfig,
exa_include_domains: undefined,
};
}
await ensurePreflight({
provider: "exa",
operation_type: "exa_neural_search",
tokens_requested: 0,
actual_provider_name: "exa",
});
const response = await aiApiClient.post("/api/podcast/research/exa", {
topic: params.topic || keywords[0],
queries: keywords,
exa_config: sanitizedExaConfig,
bible: params.bible,
analysis: params.analysis,
});
const exaResult = response.data as ExaResearchResult;
if (params.onProgress) {
params.onProgress("Deep research completed with Exa.");
}
const mapped = mapExaResearchResponse(exaResult);
return { research: mapped, raw: exaResult };
},
async generateScript(params: {
projectId: string;
idea: string;
research?: ExaResearchResult | null;
knobs: Knobs;
speakers: number;
durationMinutes: number;
bible?: any;
outline?: any;
analysis?: PodcastAnalysis | null;
}): Promise<Script> {
await ensurePreflight({
provider: "gemini",
operation_type: "script_generation",
tokens_requested: 2000,
actual_provider_name: "gemini",
});
const response = await aiApiClient.post("/api/podcast/script", {
idea: params.idea,
duration_minutes: params.durationMinutes,
speakers: params.speakers,
research: params.research,
bible: params.bible,
outline: params.outline,
analysis: params.analysis,
});
const scenes = response.data?.scenes || [];
const scriptScenes: Scene[] = scenes.map((scene: any) => ({
id: scene.id || createId("scene"),
title: scene.title || "Scene",
duration: scene.duration || Math.max(20, params.knobs.scene_length_target || DEFAULT_KNOBS.scene_length_target),
lines:
Array.isArray(scene.lines) && scene.lines.length
? scene.lines.map((l: any) => ({
id: createId("line"),
speaker: l.speaker || "Host",
text: l.text || "",
}))
: [
{
id: createId("line"),
speaker: "Host",
text: "Let's dive into today's topic.",
},
],
approved: false,
}));
return { scenes: scriptScenes };
},
async previewLine(
text: string,
options: { voiceId?: string; speed?: number; emotion?: string } = {}
): Promise<{ ok: boolean; message: string; audioUrl?: string }> {
await ensurePreflight({
provider: "audio",
operation_type: "tts_preview",
tokens_requested: text.length,
actual_provider_name: "wavespeed",
});
const response = await storyWriterApi.generateAIAudio({
scene_number: 0,
scene_title: "Preview",
text,
voice_id: options.voiceId || "Wise_Woman",
speed: options.speed || 1.0,
emotion: options.emotion || "neutral",
});
if (!response.success) {
throw new Error(response.error || "Preview failed");
}
return {
ok: true,
message: "Preview ready opening audio in new tab.",
audioUrl: response.audio_url,
};
},
async renderSceneAudio(params: {
scene: Scene;
voiceId?: string;
emotion?: string; // Fallback if scene doesn't have emotion
speed?: number;
volume?: number;
pitch?: number;
englishNormalization?: boolean;
sampleRate?: number;
bitrate?: number;
channel?: "1" | "2";
format?: "mp3" | "wav" | "pcm" | "flac";
languageBoost?: string;
}): Promise<RenderJobResult> {
// Use scene-specific emotion if available, otherwise fallback to provided/default
const sceneEmotion = params.scene.emotion || params.emotion || "neutral";
// Optimize text for Minimax Speech-02-HD TTS
// - Strip markdown formatting (bold, italic, etc.) - TTS reads it literally
// - Use pause markers <#x#> for natural speech rhythm
// - Add longer pauses for speaker changes
// - Preserve punctuation for natural breathing
// - Add emphasis pauses for important points
const text = params.scene.lines
.map((line, idx) => {
let lineText = line.text.trim();
// Strip markdown formatting - TTS reads asterisks and other markdown literally
// Remove bold (**text** or __text__)
lineText = lineText.replace(/\*\*([^*]+)\*\*/g, '$1'); // **bold**
lineText = lineText.replace(/\*([^*]+)\*/g, '$1'); // *bold* (single asterisk)
lineText = lineText.replace(/__([^_]+)__/g, '$1'); // __bold__
lineText = lineText.replace(/_([^_]+)_/g, '$1'); // _italic_ (single underscore)
// Remove any remaining stray asterisks or underscores
lineText = lineText.replace(/\*+/g, ''); // Remove any remaining asterisks
lineText = lineText.replace(/_+/g, ''); // Remove any remaining underscores
// Clean up extra spaces
lineText = lineText.replace(/\s+/g, ' ').trim();
// Preserve punctuation (Minimax uses it for natural breathing)
// Don't strip punctuation - it helps TTS understand natural pauses
// Add emphasis pause after lines marked with emphasis
if (line.emphasis) {
// Minimal pause after emphasized content (0.15s for subtle emphasis)
lineText = `${lineText}<#0.15#>`;
}
// Check for speaker change (longer pause for natural conversation flow)
const prevLine = idx > 0 ? params.scene.lines[idx - 1] : null;
const isSpeakerChange = prevLine && prevLine.speaker !== line.speaker;
if (isSpeakerChange) {
// Short pause for speaker changes (0.2s - enough for natural transition)
lineText = `<#0.2#>${lineText}`;
}
// Add minimal pause between lines (only between regular lines, very short)
if (idx < params.scene.lines.length - 1) {
if (!line.emphasis && !isSpeakerChange) {
// Very short pause between lines (0.08s - barely noticeable but helps flow)
lineText = `${lineText}<#0.08#>`;
}
// If emphasis or speaker change, the pause is already added above
}
return lineText;
})
.join(" ");
// Validate character limit (Minimax max: 10,000 characters)
const MAX_CHARS = 10000;
let textToUse = text;
if (text.length > MAX_CHARS) {
console.warn(
`[Podcast] Scene "${params.scene.title}" exceeds ${MAX_CHARS} character limit (${text.length} chars). Truncating...`
);
// Truncate at word boundary to avoid cutting mid-word
const truncated = text.substring(0, MAX_CHARS);
const lastSpace = truncated.lastIndexOf(" ");
textToUse = lastSpace > 0 ? truncated.substring(0, lastSpace) : truncated;
}
await ensurePreflight({
provider: "audio",
operation_type: "tts_full_render",
tokens_requested: textToUse.length,
actual_provider_name: "wavespeed",
});
const response = await aiApiClient.post("/api/podcast/audio", {
scene_id: params.scene.id,
scene_title: params.scene.title,
text: textToUse,
voice_id: params.voiceId || "Wise_Woman",
speed: params.speed ?? 1.0, // Normal speed (was 0.9, but too slow - causing duration issues)
volume: params.volume ?? 1.0,
pitch: params.pitch ?? 0.0,
emotion: sceneEmotion,
english_normalization: params.englishNormalization ?? true, // Better number reading for statistics
sample_rate: params.sampleRate || null,
bitrate: params.bitrate || null,
channel: params.channel || null,
format: params.format || null,
language_boost: params.languageBoost || null,
});
return {
audioUrl: response.data.audio_url,
audioFilename: response.data.audio_filename,
provider: response.data.provider,
model: response.data.model,
cost: response.data.cost,
voiceId: response.data.voice_id,
fileSize: response.data.file_size,
};
},
async approveScene(params: { projectId: string; sceneId: string; notes?: string }) {
await aiApiClient.post("/api/story/script/approve", {
project_id: params.projectId,
scene_id: params.sceneId,
approved: true,
notes: params.notes,
});
},
// Project persistence endpoints
async saveProject(projectId: string, state: any): Promise<void> {
try {
await aiApiClient.put(`/api/podcast/projects/${projectId}`, state);
} catch (error) {
console.error("Failed to save project to database:", error);
// Don't throw - localStorage fallback is acceptable
}
},
async loadProject(projectId: string): Promise<any> {
const response = await aiApiClient.get(`/api/podcast/projects/${projectId}`);
return response.data;
},
async listProjects(params?: {
status?: string;
favorites_only?: boolean;
limit?: number;
offset?: number;
order_by?: "updated_at" | "created_at";
}): Promise<{ projects: any[]; total: number; limit: number; offset: number }> {
const response = await aiApiClient.get("/api/podcast/projects", { params });
return response.data;
},
async createProjectInDb(params: {
project_id: string;
idea: string;
duration: number;
speakers: number;
budget_cap: number;
avatar_url?: string | null;
}): Promise<any> {
const response = await aiApiClient.post("/api/podcast/projects", params);
return response.data;
},
async updateProject(projectId: string, updates: any): Promise<any> {
const response = await aiApiClient.put(`/api/podcast/projects/${projectId}`, updates);
return response.data;
},
async deleteProject(projectId: string): Promise<void> {
await aiApiClient.delete(`/api/podcast/projects/${projectId}`);
},
async toggleFavorite(projectId: string): Promise<any> {
const response = await aiApiClient.post(`/api/podcast/projects/${projectId}/favorite`);
return response.data;
},
async saveAudioToAssetLibrary(params: {
audioUrl: string;
filename: string;
title: string;
description?: string;
projectId: string;
sceneId?: string;
cost?: number;
provider?: string;
model?: string;
fileSize?: number;
}): Promise<{ assetId: number }> {
const response = await aiApiClient.post("/api/content-assets/", {
asset_type: "audio",
source_module: "podcast_maker",
filename: params.filename,
file_url: params.audioUrl,
title: params.title,
description: params.description || `Podcast episode audio: ${params.title}`,
tags: ["podcast", "audio", params.projectId],
asset_metadata: {
project_id: params.projectId,
scene_id: params.sceneId,
provider: params.provider,
model: params.model,
},
provider: params.provider,
model: params.model,
cost: params.cost || 0,
file_size: params.fileSize,
mime_type: "audio/mpeg",
});
return { assetId: response.data.id };
},
async generateVideo(params: {
projectId: string;
sceneId: string;
sceneTitle: string;
audioUrl: string;
avatarImageUrl?: string;
bible?: any;
resolution?: string;
prompt?: string;
seed?: number;
maskImageUrl?: string;
}): Promise<{ taskId: string; status: string; message: string }> {
const response = await aiApiClient.post("/api/podcast/render/video", {
project_id: params.projectId,
scene_id: params.sceneId,
scene_title: params.sceneTitle,
audio_url: params.audioUrl,
avatar_image_url: params.avatarImageUrl,
bible: params.bible,
resolution: params.resolution || "720p",
prompt: params.prompt,
seed: params.seed ?? -1,
mask_image_url: params.maskImageUrl,
});
// Backend returns snake_case (task_id); normalize to camelCase for callers
const { task_id, status, message } = response.data || {};
return {
taskId: task_id,
status,
message,
};
},
async pollTaskStatus(taskId: string): Promise<TaskStatus | null> {
const response = await aiApiClient.get(`/api/podcast/task/${taskId}/status`);
// Backend returns null if task not found
return response.data || null;
},
async listVideos(projectId?: string): Promise<{
videos: Array<{
scene_number: number;
filename: string;
video_url: string;
file_size: number;
}>;
}> {
const params = projectId ? { project_id: projectId } : {};
const response = await aiApiClient.get("/api/podcast/videos", { params });
return response.data;
},
async combineVideos(params: {
projectId: string;
sceneVideoUrls: string[];
podcastTitle?: string;
}): Promise<{
taskId: string;
status: string;
message: string;
}> {
const response = await aiApiClient.post("/api/podcast/render/combine-videos", {
project_id: params.projectId,
scene_video_urls: params.sceneVideoUrls,
podcast_title: params.podcastTitle || "Podcast",
});
const { task_id, status, message } = response.data || {};
return {
taskId: task_id,
status,
message,
};
},
async generateSceneImage(params: {
sceneId: string;
sceneTitle: string;
sceneContent?: string;
baseAvatarUrl?: string;
bible?: any;
idea?: string;
width?: number;
height?: number;
customPrompt?: string;
style?: "Auto" | "Fiction" | "Realistic";
renderingSpeed?: "Default" | "Turbo" | "Quality";
aspectRatio?: "1:1" | "16:9" | "9:16" | "4:3" | "3:4";
}): Promise<{
scene_id: string;
scene_title: string;
image_filename: string;
image_url: string;
width: number;
height: number;
provider: string;
model?: string;
cost: number;
}> {
const response = await aiApiClient.post("/api/podcast/image", {
scene_id: params.sceneId,
scene_title: params.sceneTitle,
scene_content: params.sceneContent,
base_avatar_url: params.baseAvatarUrl || null,
bible: params.bible,
idea: params.idea || null,
width: params.width || 1024,
height: params.height || 1024,
custom_prompt: params.customPrompt || null,
style: params.style || null,
rendering_speed: params.renderingSpeed || null,
aspect_ratio: params.aspectRatio || null,
});
return response.data;
},
async cancelTask(taskId: string): Promise<void> {
// Note: Task cancellation may not be fully supported by backend yet
// This is a placeholder for future implementation
try {
await aiApiClient.post(`/api/story/task/${taskId}/cancel`);
} catch (error) {
console.warn("Task cancellation not supported:", error);
}
},
async combineAudio(params: {
projectId: string;
sceneIds: string[];
sceneAudioUrls: string[];
}): Promise<{
combined_audio_url: string;
combined_audio_filename: string;
total_duration: number;
file_size: number;
scene_count: number;
}> {
const response = await aiApiClient.post("/api/podcast/combine-audio", {
project_id: params.projectId,
scene_ids: params.sceneIds,
scene_audio_urls: params.sceneAudioUrls,
});
return response.data;
},
async uploadAvatar(file: File, projectId?: string): Promise<{ avatar_url: string; avatar_filename: string }> {
const formData = new FormData();
formData.append('file', file);
if (projectId) {
formData.append('project_id', projectId);
}
const response = await aiApiClient.post('/api/podcast/avatar/upload', formData, {
headers: { 'Content-Type': 'multipart/form-data' },
});
return response.data;
},
async generatePresenters(
speakers: number,
projectId?: string,
audience?: string,
contentType?: string,
topKeywords?: string[]
): Promise<{
avatars: Array<{ avatar_url: string; speaker_number: number; prompt?: string; persona_id?: string; seed?: number }>;
persona_id?: string;
}> {
const formData = new FormData();
formData.append('speakers', speakers.toString());
if (projectId) {
formData.append('project_id', projectId);
}
if (audience) {
formData.append('audience', audience);
}
if (contentType) {
formData.append('content_type', contentType);
}
if (topKeywords && Array.isArray(topKeywords) && topKeywords.length > 0) {
formData.append('top_keywords', JSON.stringify(topKeywords));
}
const response = await aiApiClient.post('/api/podcast/avatar/generate', formData, {
headers: { 'Content-Type': 'multipart/form-data' },
});
return response.data;
},
async makeAvatarPresentable(avatarUrl: string, projectId?: string): Promise<{ avatar_url: string; avatar_filename: string }> {
const formData = new FormData();
formData.append('avatar_url', avatarUrl);
if (projectId) {
formData.append('project_id', projectId);
}
const response = await aiApiClient.post('/api/podcast/avatar/make-presentable', formData, {
headers: { 'Content-Type': 'multipart/form-data' },
});
return response.data;
},
};
export type PodcastApi = typeof podcastApi;

244
_session_backup/research.py Normal file
View File

@@ -0,0 +1,244 @@
"""
Podcast Research Handlers
Research endpoints using Exa provider and LLM summarization.
"""
from fastapi import APIRouter, Depends, HTTPException
from typing import Dict, Any, List
from types import SimpleNamespace
import json
from middleware.auth_middleware import get_current_user
from api.story_writer.utils.auth import require_authenticated_user
from services.blog_writer.research.exa_provider import ExaResearchProvider
from services.llm_providers.main_text_generation import llm_text_gen
from services.podcast_bible_service import PodcastBibleService
from loguru import logger
from ..models import (
PodcastExaResearchRequest,
PodcastExaResearchResponse,
PodcastExaSource,
PodcastExaConfig,
PodcastResearchInsight,
)
router = APIRouter()
@router.post("/research/exa", response_model=PodcastExaResearchResponse)
async def podcast_research_exa(
request: PodcastExaResearchRequest,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""
Run podcast research via Exa and then use LLM to extract deep insights.
Uses Podcast Bible and Analysis context for hyper-personalization.
"""
user_id = require_authenticated_user(current_user)
queries = [q.strip() for q in request.queries if q and q.strip()]
if not queries:
raise HTTPException(status_code=400, detail="At least one query is required for research.")
exa_cfg = request.exa_config or PodcastExaConfig()
cfg = SimpleNamespace(
exa_search_type=exa_cfg.exa_search_type or "auto",
exa_category=exa_cfg.exa_category,
exa_include_domains=exa_cfg.exa_include_domains or [],
exa_exclude_domains=exa_cfg.exa_exclude_domains or [],
max_sources=exa_cfg.max_sources or 8,
source_types=[],
)
provider = ExaResearchProvider()
# --- Context Building ---
bible_service = PodcastBibleService()
bible_context = ""
if request.bible:
try:
from models.podcast_bible_models import PodcastBible
bible_data = PodcastBible(**request.bible)
bible_context = bible_service.serialize_bible(bible_data)
except Exception as exc:
logger.warning(f"[Podcast Research] Failed to serialize bible: {exc}")
analysis_context = ""
if request.analysis:
analysis_context = f"""
PODCAST ANALYSIS CONTEXT:
Audience: {request.analysis.get('audience', 'General')}
Content Type: {request.analysis.get('content_type', 'Informative')}
Top Keywords: {', '.join(request.analysis.get('top_keywords', []))}
"""
# Exa search params
industry = request.bible.get("brand", {}).get("industry", "") if request.bible else ""
target_audience = ""
if request.bible:
audience_dna = request.bible.get("audience", {})
if audience_dna:
interests = ", ".join(audience_dna.get("interests", []))
target_audience = f"Expertise: {audience_dna.get('expertise_level', '')}. Interests: {interests}."
try:
# 1. RUN EXA SEARCH
result = await provider.search(
prompt=request.topic,
topic=request.topic,
industry=industry,
target_audience=target_audience,
config=cfg,
user_id=user_id,
)
except Exception as exc:
logger.error(f"[Podcast Exa Research] Search failed for user {user_id}: {exc}")
raise HTTPException(status_code=500, detail=f"Exa research failed: {exc}")
# 2. EXTRACT INSIGHTS VIA LLM
raw_content = result.get("content", "")
sources = result.get("sources", [])
summary = ""
key_insights = []
expert_quotes = []
listener_cta = []
mapped_angles = []
if raw_content and sources:
logger.info(f"[Podcast Research] Extracting insights from {len(sources)} sources for user {user_id}")
prompt = f"""
You are an expert research analyst for a high-end podcast production team.
Your task is to analyze the following research data and extract deep, actionable insights for a podcast episode.
PODCAST CONTEXT:
Topic: {request.topic}
{bible_context}
{analysis_context}
RESEARCH DATA (from {len(sources)} sources):
{raw_content}
TASK:
1. Provide a comprehensive summary (2-3 paragraphs) of the most important findings. Use Markdown for formatting (bolding, lists).
2. Extract 3-5 "Key Insights". Each insight should have a title and a detailed explanation.
3. For each insight, identify which source indices (e.g. 1, 2) it was derived from.
4. Extract notable "Expert Quotes" - direct quotes from industry leaders, researchers, or authoritative voices found in the sources.
5. Suggest 2-4 "Listener CTA" (call-to-action) ideas that the podcast host can use to engage the audience.
6. Identify 3-5 "Mapped Angles" - unique content angles with rationale for why they matter for this topic.
NOTE: The research data includes "Key Highlights", "Summaries", and "Excerpts" from various sources.
Pay special attention to the "Key Highlights" sections as they contain the most relevant information extracted by the neural search engine.
Return JSON structure:
{{
"summary": "Detailed markdown summary...",
"key_insights": [
{{
"title": "Insight Title",
"content": "Detailed markdown content...",
"source_indices": [1, 2]
}}
],
"expert_quotes": [
{{
"quote": "Exact quote from source...",
"source_index": 1
}}
],
"listener_cta": [
"Call-to-action suggestion 1",
"Call-to-action suggestion 2"
],
"mapped_angles": [
{{
"title": "Angle Title",
"why": "Why this angle matters for the audience...",
"mapped_fact_ids": ["fact_1", "fact_2"]
}}
]
}}
Requirements:
- Ensure insights are deep, not just superficial facts. Look for trends, expert opinions, and specific data points.
- Expert quotes should be exact or near-exact quotes from the sources, with attribution.
- Listener CTAs should be practical and engaging (e.g., "Share your experience with X on social media").
- Mapped angles should be unique perspectives that make the episode stand out.
- Tone should be professional, insightful, and ready for a podcast host to discuss.
- Avoid generic filler.
"""
try:
llm_response = llm_text_gen(
prompt=prompt,
user_id=user_id,
json_struct=None,
preferred_provider="huggingface",
flow_type="premium_tool",
)
# Normalize response
if isinstance(llm_response, str):
data = json.loads(llm_response)
else:
data = llm_response
summary = data.get("summary", "")
key_insights = [PodcastResearchInsight(**insight) for insight in data.get("key_insights", [])]
expert_quotes = data.get("expert_quotes", [])
listener_cta = data.get("listener_cta", [])
mapped_angles = data.get("mapped_angles", [])
except Exception as exc:
logger.error(f"[Podcast Research] LLM Insight extraction failed: {exc}")
# Fallback to a basic summary if LLM fails
summary = f"Research completed for '{request.topic}'. Found {len(sources)} sources."
# Fallback: if summary is still empty (e.g. LLM returned empty string), use raw content first paragraph or basic text
if not summary:
if raw_content:
summary = raw_content[:2000] # Use first 2000 chars of raw content as summary
else:
summary = f"Research completed for '{request.topic}'. Found {len(sources)} sources."
# 3. TRACK USAGE
try:
cost_total = 0.0
if isinstance(result, dict):
cost_total = result.get("cost", {}).get("total", 0.005) if result.get("cost") else 0.005
provider.track_exa_usage(user_id, cost_total)
except Exception as track_err:
logger.warning(f"[Podcast Exa Research] Failed to track usage: {track_err}")
sources_payload = []
for src in sources:
try:
sources_payload.append(PodcastExaSource(**src))
except Exception:
sources_payload.append(PodcastExaSource(**{
"title": src.get("title", ""),
"url": src.get("url", ""),
"excerpt": src.get("excerpt", ""),
"published_at": src.get("published_at"),
"highlights": src.get("highlights"),
"summary": src.get("summary"),
"source_type": src.get("source_type"),
"index": src.get("index"),
"image": src.get("image"),
"author": src.get("author"),
}))
return PodcastExaResearchResponse(
sources=sources_payload,
search_queries=result.get("search_queries", queries) if isinstance(result, dict) else queries,
summary=summary,
key_insights=key_insights,
expert_quotes=expert_quotes,
listener_cta=listener_cta,
mapped_angles=mapped_angles,
cost=result.get("cost") if isinstance(result, dict) else None,
search_type=result.get("search_type") if isinstance(result, dict) else None,
provider=result.get("provider", "exa") if isinstance(result, dict) else "exa",
content=raw_content,
)

183
_session_backup/script.py Normal file
View File

@@ -0,0 +1,183 @@
"""
Podcast Script Handlers
Script generation endpoint.
"""
from fastapi import APIRouter, Depends, HTTPException
from typing import Dict, Any
import json
from middleware.auth_middleware import get_current_user
from api.story_writer.utils.auth import require_authenticated_user
from services.llm_providers.main_text_generation import llm_text_gen
from services.podcast_bible_service import PodcastBibleService
from models.podcast_bible_models import PodcastBible
from loguru import logger
from ..models import (
PodcastScriptRequest,
PodcastScriptResponse,
PodcastScene,
PodcastSceneLine,
)
router = APIRouter()
@router.post("/script", response_model=PodcastScriptResponse)
async def generate_podcast_script(
request: PodcastScriptRequest,
current_user: Dict[str, Any] = Depends(get_current_user),
):
"""
Generate a podcast script outline (scenes + lines) using podcast-oriented prompting.
"""
user_id = require_authenticated_user(current_user)
# Build comprehensive research context for higher-quality scripts
research_context = ""
if request.research:
try:
key_insights = request.research.get("keyword_analysis", {}).get("key_insights") or []
fact_cards = request.research.get("factCards", []) or []
mapped_angles = request.research.get("mappedAngles", []) or []
sources = request.research.get("sources", []) or []
top_facts = [f.get("quote", "") for f in fact_cards[:5] if f.get("quote")]
angles_summary = [
f"{a.get('title', '')}: {a.get('why', '')}" for a in mapped_angles[:3] if a.get("title") or a.get("why")
]
top_sources = [s.get("url") for s in sources[:3] if s.get("url")]
research_parts = []
if key_insights:
research_parts.append(f"Key Insights: {', '.join(key_insights[:5])}")
if top_facts:
research_parts.append(f"Key Facts: {', '.join(top_facts)}")
if angles_summary:
research_parts.append(f"Research Angles: {' | '.join(angles_summary)}")
if top_sources:
research_parts.append(f"Top Sources: {', '.join(top_sources)}")
research_context = "\n".join(research_parts)
except Exception as exc:
logger.warning(f"Failed to parse research context: {exc}")
research_context = ""
# Extract Podcast Bible context for hyper-personalization
bible_context = ""
if request.bible:
try:
bible_service = PodcastBibleService()
bible_obj = PodcastBible(**request.bible)
bible_context = bible_service.serialize_bible(bible_obj)
except Exception as exc:
logger.warning(f"Failed to serialize podcast bible: {exc}")
# Extract Analysis and Outline context for grounding
analysis_context = ""
if request.analysis:
analysis_context = f"""
TARGET AUDIENCE: {request.analysis.get('audience', 'General')}
CONTENT TYPE: {request.analysis.get('contentType', 'Conversational')}
TOP KEYWORDS: {', '.join(request.analysis.get('topKeywords', []))}
"""
outline_context = ""
if request.outline:
outline_context = f"""
REFINED EPISODE OUTLINE (Follow this structure closely):
Title: {request.outline.get('title', 'N/A')}
Segments: {' | '.join(request.outline.get('segments', []))}
"""
prompt = f"""You are an expert podcast script planner. Create natural, conversational podcast scenes.
{f"PODCAST BIBLE (Hyper-Personalization Context):\n{bible_context}\n" if bible_context else ""}
{f"ANALYSIS CONTEXT:\n{analysis_context}\n" if analysis_context else ""}
{f"REFINED OUTLINE:\n{outline_context}\n" if outline_context else ""}
Podcast Idea: "{request.idea}"
Duration: ~{request.duration_minutes} minutes
Speakers: {request.speakers} (Host + optional Guest)
{f"RESEARCH CONTEXT:\n{research_context}\n" if research_context else ""}
Return JSON with:
- scenes: array of scenes. Each scene has:
- id: string
- title: short scene title (<= 60 chars)
- duration: duration in seconds (evenly split across total duration)
- emotion: string (one of: "neutral", "happy", "excited", "serious", "curious", "confident")
- lines: array of {{"speaker": "...", "text": "...", "emphasis": boolean}}
* Write natural, conversational dialogue
* Each line can be a sentence or a few sentences that flow together
* Use plain text only - no markdown formatting (no asterisks, underscores, etc.)
* Mark "emphasis": true for key statistics or important points
Guidelines:
- Write for spoken delivery: conversational, natural, with contractions.
- Follow the interaction tone specified in the Bible.
- Ensure the Host persona matches the background and personality traits from the Bible.
- Structure the intro and outro scenes according to the Bible's "Intro Format" and "Outro Format".
- Adhere to any constraints mentioned in the Bible.
- Use insights from the Research Context to ground the conversation in facts.
- IMPORTANT: Follow the REFINED OUTLINE segments as the primary structure for the episode.
"""
try:
raw = llm_text_gen(
prompt=prompt,
user_id=user_id,
json_struct=None,
preferred_provider="huggingface",
flow_type="premium_tool",
)
except Exception as exc:
raise HTTPException(status_code=500, detail=f"Script generation failed: {exc}")
if isinstance(raw, str):
try:
data = json.loads(raw)
except json.JSONDecodeError:
raise HTTPException(status_code=500, detail="LLM returned non-JSON output")
elif isinstance(raw, dict):
data = raw
else:
raise HTTPException(status_code=500, detail="Unexpected LLM response format")
scenes_data = data.get("scenes") or []
if not isinstance(scenes_data, list):
raise HTTPException(status_code=500, detail="LLM response missing scenes array")
valid_emotions = {"neutral", "happy", "excited", "serious", "curious", "confident"}
# Normalize scenes
scenes: list[PodcastScene] = []
for idx, scene in enumerate(scenes_data):
title = scene.get("title") or f"Scene {idx + 1}"
duration = int(scene.get("duration") or max(30, (request.duration_minutes * 60) // max(1, len(scenes_data))))
emotion = scene.get("emotion") or "neutral"
if emotion not in valid_emotions:
emotion = "neutral"
lines_raw = scene.get("lines") or []
lines: list[PodcastSceneLine] = []
for line in lines_raw:
speaker = line.get("speaker") or ("Host" if len(lines) % request.speakers == 0 else "Guest")
text = line.get("text") or ""
emphasis = line.get("emphasis", False)
if text:
lines.append(PodcastSceneLine(speaker=speaker, text=text, emphasis=emphasis))
scenes.append(
PodcastScene(
id=scene.get("id") or f"scene-{idx + 1}",
title=title,
duration=duration,
lines=lines,
approved=False,
emotion=emotion,
)
)
return PodcastScriptResponse(scenes=scenes)

209
_session_backup/types.ts Normal file
View File

@@ -0,0 +1,209 @@
export type Knobs = {
voice_emotion: string;
voice_speed: number;
resolution: string;
scene_length_target: number;
sample_rate: number;
bitrate: string;
};
export type Query = {
id: string;
query: string;
rationale: string;
needsRecentStats: boolean;
};
export type Fact = {
id: string;
quote: string;
url: string;
date: string;
confidence: number;
image?: string;
author?: string;
highlights?: string[];
};
export type ResearchInsight = {
title: string;
content: string;
source_indices: number[];
};
export type Research = {
summary: string;
keyInsights: ResearchInsight[];
factCards: Fact[];
mappedAngles: {
title: string;
why: string;
mappedFactIds: string[];
}[];
searchQueries?: string[];
searchType?: string;
provider?: string;
cost?: number;
sourceCount?: number;
expertQuotes?: { quote: string; source_index: number }[];
listenerCta?: string[];
};
export type Line = {
id: string;
speaker: string;
text: string;
usedFactIds?: string[];
emphasis?: boolean; // Mark lines that need vocal emphasis
};
export type Scene = {
id: string;
title: string;
duration: number;
lines: Line[];
approved?: boolean;
emotion?: string; // Scene-specific emotion
audioUrl?: string; // Generated audio URL for this scene
imageUrl?: string; // Generated image URL for this scene (for video generation)
};
export type Script = {
scenes: Scene[];
};
export type JobStatus =
| "idle"
| "previewing"
| "queued"
| "running"
| "completed"
| "cancelled"
| "failed";
export type Job = {
sceneId: string;
title: string;
status: JobStatus;
progress: number;
previewUrl?: string | null;
finalUrl?: string | null;
videoUrl?: string | null;
jobId?: string | null;
taskId?: string | null;
cost?: number | null;
provider?: string | null;
voiceId?: string | null;
fileSize?: number | null;
avatarImageUrl?: string | null;
imageUrl?: string | null; // Scene-specific image URL
};
export type PodcastAnalysis = {
audience: string;
contentType: string;
topKeywords: string[];
suggestedOutlines: { id: number | string; title: string; segments: string[] }[];
suggestedKnobs: Knobs;
titleSuggestions: string[];
research_queries?: { query: string; rationale: string }[];
exaSuggestedConfig?: {
exa_search_type?: "auto" | "keyword" | "neural";
exa_category?: string;
exa_include_domains?: string[];
exa_exclude_domains?: string[];
max_sources?: number;
include_statistics?: boolean;
date_range?: string;
};
};
export type PodcastEstimate = {
ttsCost: number;
avatarCost: number;
videoCost: number;
researchCost: number;
total: number;
};
export type HostPersona = {
name: string;
background: string;
expertise_level: string;
personality_traits: string[];
vocal_style: string;
catchphrases: string[];
};
export type AudienceDNA = {
expertise_level: string;
interests: string[];
pain_points: string[];
demographics?: string;
};
export type BrandDNA = {
industry: string;
tone: string;
communication_style: string;
key_messages: string[];
competitor_context?: string;
};
export type PodcastBible = {
project_id?: string;
host: HostPersona;
audience: AudienceDNA;
brand: BrandDNA;
};
export type CreateProjectPayload = {
ideaOrUrl: string;
speakers: number;
duration: number;
knobs: Knobs;
budgetCap: number;
files: { voiceFile?: File | null; avatarFile?: File | null };
avatarUrl?: string | null;
};
export type CreateProjectResult = {
projectId: string;
analysis: PodcastAnalysis;
estimate: PodcastEstimate;
queries: Query[];
bible?: PodcastBible;
avatar_url?: string | null;
avatar_prompt?: string | null;
};
export type RenderJobResult = {
audioUrl: string;
audioFilename: string;
provider: string;
model: string;
cost: number;
voiceId: string;
fileSize: number;
videoUrl?: string;
videoFilename?: string;
};
export interface VideoGenerationSettings {
prompt: string;
resolution: "480p" | "720p";
seed?: number | null;
maskImageUrl?: string | null;
}
export type TaskStatus = {
task_id: string;
status: "pending" | "processing" | "completed" | "failed";
progress?: number;
message?: string;
result?: any;
error?: string;
created_at?: string;
updated_at?: string;
};

View File

@@ -0,0 +1,425 @@
import { useState, useEffect, useMemo, useCallback } from "react";
import { podcastApi } from "../../../services/podcastApi";
import { usePreflightCheck } from "../../../hooks/usePreflightCheck";
import { useBudgetTracking } from "../../../hooks/useBudgetTracking";
import { CreateProjectPayload, Script } from "../types";
import { usePodcastProjectState } from "../../../hooks/usePodcastProjectState";
import { sanitizeExaConfig, announceError, getStepLabel } from "./utils";
type PodcastProjectStateReturn = ReturnType<typeof usePodcastProjectState>;
interface UsePodcastWorkflowProps {
projectState: PodcastProjectStateReturn;
onError: (message: string) => void;
}
export const usePodcastWorkflow = ({ projectState, onError }: UsePodcastWorkflowProps) => {
const {
project,
analysis,
queries,
selectedQueries,
research,
rawResearch,
researchProvider,
showScriptEditor,
showRenderQueue,
currentStep,
renderJobs,
budgetCap,
setProject,
setAnalysis,
setQueries,
setSelectedQueries,
setResearch,
setRawResearch,
setEstimate,
setScriptData,
setShowScriptEditor,
setShowRenderQueue,
setKnobs,
setResearchProvider,
setBudgetCap,
updateRenderJob,
initializeProject,
setBible,
} = projectState;
const [isAnalyzing, setIsAnalyzing] = useState(false);
const [isResearching, setIsResearching] = useState(false);
const [announcement, setAnnouncement] = useState("");
const [showResumeAlert, setShowResumeAlert] = useState(false);
const [showPreflightDialog, setShowPreflightDialog] = useState(false);
const [preflightResponse, setPreflightResponse] = useState<any>(null);
const [preflightOperationName, setPreflightOperationName] = useState<string>("");
const budgetTracking = useBudgetTracking(budgetCap || 50);
const preflightCheck = usePreflightCheck({
onBlocked: (response) => {
setPreflightResponse(response);
setShowPreflightDialog(true);
},
});
// Update budget cap when project state changes
useEffect(() => {
if (budgetCap) {
budgetTracking.setBudgetCap(budgetCap);
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [budgetCap]);
// Check if we have a saved project on mount
useEffect(() => {
if (project && currentStep && currentStep !== "create") {
setShowResumeAlert(true);
setTimeout(() => setShowResumeAlert(false), 5000);
}
}, [project, currentStep]);
useEffect(() => {
if (announcement) {
const t = setTimeout(() => setAnnouncement(""), 4000);
return () => clearTimeout(t);
}
return undefined;
}, [announcement]);
const handleCreate = useCallback(async (payload: CreateProjectPayload, feedback?: string) => {
if (isAnalyzing) return;
setResearch(null);
setRawResearch(null);
setScriptData(null);
setShowScriptEditor(false);
setShowRenderQueue(false);
try {
setIsAnalyzing(true);
// Use existing avatar URL if provided (e.g. brand avatar), or upload new file
let avatarUrl: string | null = payload.avatarUrl || null;
if (payload.files.avatarFile) {
try {
setAnnouncement("Uploading presenter avatar...");
const uploadResponse = await podcastApi.uploadAvatar(payload.files.avatarFile);
avatarUrl = uploadResponse.avatar_url;
} catch (error) {
console.error('Avatar upload failed:', error);
// Continue without avatar - will generate one later
}
}
// NEW FLOW: Create project first to generate/get the Podcast Bible
// This allows the analysis to be personalized using the Bible context
const projectId = project?.id || `podcast_${Date.now()}_${Math.floor(Math.random() * 1000)}`;
setAnnouncement("Initializing project and brand context...");
const dbProject = project ? null : await initializeProject(payload, projectId, avatarUrl);
const bible = dbProject?.bible || projectState.bible;
setAnnouncement(feedback ? "Regenerating analysis using your feedback..." : "Analyzing your idea — AI suggestions incoming");
const result = await podcastApi.createProject(payload, bible, feedback);
if (result.bible) {
setBible(result.bible);
} else if (dbProject?.bible) {
setBible(dbProject.bible);
}
// Update the project in database with the analysis results
try {
await podcastApi.updateProject(projectId, {
analysis: result.analysis,
estimate: result.estimate,
queries: result.queries,
selected_queries: result.queries.map(q => q.id),
avatar_url: result.avatar_url,
avatar_prompt: result.avatar_prompt,
});
} catch (error) {
console.error('Failed to update project with analysis results:', error);
}
setProject({
id: projectId,
idea: payload.ideaOrUrl,
duration: payload.duration,
speakers: payload.speakers,
avatarUrl: result.avatar_url || avatarUrl,
avatarPrompt: result.avatar_prompt || null,
avatarPersonaId: null,
});
setAnalysis(result.analysis);
setEstimate(result.estimate);
setQueries(result.queries);
setSelectedQueries(new Set(result.queries.map((q) => q.id)));
setKnobs(payload.knobs);
setBudgetCap(payload.budgetCap);
// Generate presenters AFTER analysis completes (to use analysis insights)
// This happens only if no avatar was uploaded
if (!avatarUrl && payload.speakers > 0 && result.analysis) {
try {
setAnnouncement("Generating presenter avatars using AI insights...");
const presentersResponse = await podcastApi.generatePresenters(
payload.speakers,
result.projectId,
result.analysis.audience,
result.analysis.contentType,
result.analysis.topKeywords
);
if (presentersResponse.avatars && presentersResponse.avatars.length > 0) {
// Store the first presenter avatar URL and prompt
const firstAvatar = presentersResponse.avatars[0];
const prompt = firstAvatar.prompt || null;
setProject({
id: result.projectId,
idea: payload.ideaOrUrl,
duration: payload.duration,
speakers: payload.speakers,
avatarUrl: firstAvatar.avatar_url,
avatarPrompt: prompt,
avatarPersonaId: firstAvatar.persona_id || presentersResponse.persona_id || null,
});
setAnnouncement("Analysis complete - Presenter avatars generated");
}
} catch (error) {
console.error('Presenter generation failed:', error);
setAnnouncement("Analysis complete - Avatar generation will happen later");
// Continue without presenters - can generate later
}
} else {
setAnnouncement("Analysis complete");
}
} catch (error: any) {
if (error?.response?.status === 429 || error?.response?.data?.detail) {
const errorDetail = error.response.data.detail;
if (typeof errorDetail === 'object' && errorDetail.error && errorDetail.error.includes('limit')) {
const usageInfo = errorDetail.usage_info || {};
const blockedResponse = {
can_proceed: false,
estimated_cost: 0,
operations: [{
provider: errorDetail.provider || 'huggingface',
operation_type: 'ai_text_generation',
cost: 0,
allowed: false,
limit_info: usageInfo.limit_info || null,
message: errorDetail.message || errorDetail.error || 'Subscription limit exceeded',
}],
total_cost: 0,
usage_summary: usageInfo.usage_summary || null,
cached: false,
};
setPreflightResponse(blockedResponse);
setPreflightOperationName('Podcast Analysis');
setShowPreflightDialog(true);
setAnnouncement("Subscription limit reached. Please upgrade to continue.");
} else {
const message = typeof errorDetail === 'string' ? errorDetail : errorDetail.message || errorDetail.error || 'Request limit exceeded';
announceError(setAnnouncement, new Error(message));
}
} else {
announceError(setAnnouncement, error);
}
} finally {
setIsAnalyzing(false);
}
}, [isAnalyzing, setResearch, setRawResearch, setScriptData, setShowScriptEditor, setShowRenderQueue, initializeProject, setProject, setAnalysis, setEstimate, setQueries, setSelectedQueries, setKnobs, setBudgetCap, setBible]);
const handleRunResearch = useCallback(async () => {
if (isResearching) return;
if (!project) {
setAnnouncement("Create a project first.");
return;
}
if (selectedQueries.size === 0) {
setAnnouncement("Select at least one query to research.");
return;
}
setPreflightOperationName("Research");
const approvedQueries = queries.filter((q) => selectedQueries.has(q.id));
const preflightResult = await preflightCheck.check({
provider: researchProvider === "exa" ? "exa" : "gemini",
operation_type: researchProvider === "exa" ? "exa_neural_search" : "google_grounding",
tokens_requested: researchProvider === "exa" ? 0 : 1200,
actual_provider_name: researchProvider || "exa",
});
if (!preflightResult.can_proceed) {
return;
}
try {
setIsResearching(true);
setAnnouncement(`Starting ${researchProvider === "exa" ? "deep" : "standard"} research — this may take a moment...`);
setResearch(null);
setRawResearch(null);
setScriptData(null);
setShowScriptEditor(false);
setShowRenderQueue(false);
try {
const { research: mapped, raw } = await podcastApi.runResearch({
projectId: project.id,
topic: project.idea,
approvedQueries,
provider: researchProvider,
exaConfig: sanitizeExaConfig(analysis?.exaSuggestedConfig),
bible: projectState.bible,
analysis: analysis,
onProgress: (message) => {
setAnnouncement(message);
},
});
setResearch(mapped);
setRawResearch(raw);
setAnnouncement("Research complete — review fact cards below");
} catch (researchError) {
const errorMessage = researchError instanceof Error
? researchError.message
: "Research failed. Please try again or switch to Standard Research.";
if (errorMessage.includes("Exa") || errorMessage.includes("exa")) {
setAnnouncement(`Deep research failed: ${errorMessage}. Try Standard Research instead.`);
} else if (errorMessage.includes("timeout")) {
setAnnouncement("Research timed out. Please try again with fewer queries.");
} else {
setAnnouncement(`Research failed: ${errorMessage}`);
}
console.error("Research error:", researchError);
throw researchError;
}
} catch (error) {
announceError(setAnnouncement, error);
} finally {
setIsResearching(false);
}
}, [isResearching, project, selectedQueries, queries, researchProvider, preflightCheck, analysis, setResearch, setRawResearch, setScriptData, setShowScriptEditor, setShowRenderQueue, projectState.bible]);
const handleGenerateScript = useCallback(async () => {
if (showScriptEditor) return;
if (!project || !research) {
setAnnouncement("Project or research missing — cannot generate script");
return;
}
setPreflightOperationName("Script Generation");
const preflightResult = await preflightCheck.check({
provider: "gemini",
operation_type: "script_generation",
tokens_requested: 2000,
actual_provider_name: "gemini",
});
if (!preflightResult.can_proceed) {
return;
}
setScriptData(null);
setShowRenderQueue(false);
setShowScriptEditor(true);
try {
const result = await podcastApi.generateScript({
projectId: project.id,
idea: project.idea,
research: rawResearch,
knobs: projectState.knobs,
speakers: project.speakers,
durationMinutes: project.duration,
bible: projectState.bible,
outline: analysis?.suggestedOutlines?.[0], // Pass the first (possibly refined) outline
analysis: analysis, // Pass full analysis context
});
setScriptData(result);
} catch (error) {
announceError(setAnnouncement, error);
}
}, [showScriptEditor, project, research, preflightCheck, setScriptData, setShowRenderQueue, setShowScriptEditor, rawResearch, projectState.knobs, projectState.bible])
const handleProceedToRendering = useCallback((script: Script) => {
setScriptData(script);
if (renderJobs.length === 0) {
script.scenes.forEach((scene) => {
const hasExistingAudio = Boolean(scene.audioUrl);
updateRenderJob(scene.id, {
sceneId: scene.id,
title: scene.title,
status: hasExistingAudio ? ("completed" as const) : ("idle" as const),
progress: hasExistingAudio ? 100 : 0,
previewUrl: null,
finalUrl: hasExistingAudio ? scene.audioUrl : null,
jobId: null,
});
});
}
setShowRenderQueue(true);
setShowScriptEditor(false);
}, [renderJobs.length, setScriptData, updateRenderJob, setShowRenderQueue, setShowScriptEditor]);
const toggleQuery = useCallback((id: string) => {
if (isResearching) return;
const current = selectedQueries;
const next = new Set<string>(current);
if (next.has(id)) next.delete(id);
else next.add(id);
setSelectedQueries(next);
}, [isResearching, selectedQueries, setSelectedQueries]);
const activeStep = useMemo(() => {
if (showRenderQueue) return 3;
if (showScriptEditor) return 2;
if (currentStep === 'research' || research) return 1;
if (currentStep === 'analysis' || analysis) return 0;
return -1;
}, [showRenderQueue, showScriptEditor, currentStep, research, analysis]);
const canGenerateScript = Boolean(project && research && rawResearch);
const handleRegenerate = useCallback(async (feedback?: string) => {
if (!project) return;
// Prepare the payload from existing project state
const payload: CreateProjectPayload = {
ideaOrUrl: project.idea,
duration: project.duration,
speakers: project.speakers,
knobs: projectState.knobs,
budgetCap: projectState.budgetCap,
avatarUrl: project.avatarUrl,
files: {} // No new files for regeneration
};
await handleCreate(payload, feedback);
}, [project, projectState.knobs, projectState.budgetCap, handleCreate]);
return {
// State
isAnalyzing,
isResearching,
announcement,
showResumeAlert,
showPreflightDialog,
preflightResponse,
preflightOperationName,
activeStep,
canGenerateScript,
// Handlers
handleCreate,
handleRegenerate,
handleRunResearch,
handleGenerateScript,
handleProceedToRendering,
toggleQuery,
setAnnouncement,
setShowResumeAlert,
setShowPreflightDialog,
setPreflightResponse,
setResearchProvider,
getStepLabel,
};
};

184
add_missing_columns.py Normal file
View File

@@ -0,0 +1,184 @@
#!/usr/bin/env python3
"""
Migration script to add missing columns to usage_summaries table.
Run this once to fix the database schema.
Usage:
python add_missing_columns.py
"""
import sqlite3
from pathlib import Path
def get_db_path():
"""Find the database path."""
possible_paths = [
Path(__file__).parent / "backend" / "alwrity.db",
Path(__file__).parent.parent / "backend" / "alwrity.db",
Path("C:/Users/diksha rawat/Desktop/ALwrity_github/windsurf/ALwrity/backend/alwrity.db"),
]
for db_path in possible_paths:
if db_path.exists():
print(f"Using database: {db_path}")
return db_path
backend_dir = Path(__file__).parent / "backend"
if backend_dir.exists():
db_files = list(backend_dir.glob("*.db"))
if db_files:
print(f"Found database: {db_files[0]}")
return db_files[0]
raise FileNotFoundError(f"Database not found. Searched: {possible_paths}")
def create_usage_summaries_table(cursor):
"""Create the usage_summaries table if it doesn't exist."""
cursor.execute("""
CREATE TABLE IF NOT EXISTS usage_summaries (
id INTEGER PRIMARY KEY AUTOINCREMENT,
user_id VARCHAR(100) NOT NULL,
billing_period VARCHAR(20) NOT NULL,
-- API Call Counts
gemini_calls INTEGER DEFAULT 0,
openai_calls INTEGER DEFAULT 0,
anthropic_calls INTEGER DEFAULT 0,
mistral_calls INTEGER DEFAULT 0,
wavespeed_calls INTEGER DEFAULT 0,
tavily_calls INTEGER DEFAULT 0,
serper_calls INTEGER DEFAULT 0,
metaphor_calls INTEGER DEFAULT 0,
firecrawl_calls INTEGER DEFAULT 0,
stability_calls INTEGER DEFAULT 0,
exa_calls INTEGER DEFAULT 0,
video_calls INTEGER DEFAULT 0,
image_edit_calls INTEGER DEFAULT 0,
audio_calls INTEGER DEFAULT 0,
-- Token Usage
gemini_tokens INTEGER DEFAULT 0,
openai_tokens INTEGER DEFAULT 0,
anthropic_tokens INTEGER DEFAULT 0,
mistral_tokens INTEGER DEFAULT 0,
wavespeed_tokens INTEGER DEFAULT 0,
-- Cost Tracking
gemini_cost REAL DEFAULT 0.0,
openai_cost REAL DEFAULT 0.0,
anthropic_cost REAL DEFAULT 0.0,
mistral_cost REAL DEFAULT 0.0,
wavespeed_cost REAL DEFAULT 0.0,
tavily_cost REAL DEFAULT 0.0,
serper_cost REAL DEFAULT 0.0,
metaphor_cost REAL DEFAULT 0.0,
firecrawl_cost REAL DEFAULT 0.0,
stability_cost REAL DEFAULT 0.0,
exa_cost REAL DEFAULT 0.0,
video_cost REAL DEFAULT 0.0,
image_edit_cost REAL DEFAULT 0.0,
audio_cost REAL DEFAULT 0.0,
-- Totals
total_calls INTEGER DEFAULT 0,
total_tokens INTEGER DEFAULT 0,
total_cost REAL DEFAULT 0.0,
-- Performance Metrics
avg_response_time REAL DEFAULT 0.0,
error_rate REAL DEFAULT 0.0,
usage_status VARCHAR(20) DEFAULT 'active',
warnings_sent INTEGER DEFAULT 0,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
UNIQUE(user_id, billing_period)
)
""")
print("Created usage_summaries table")
def add_missing_columns():
db_path = get_db_path()
print(f"Using database: {db_path}")
conn = sqlite3.connect(db_path)
cursor = conn.cursor()
# Check what tables exist
cursor.execute("SELECT name FROM sqlite_master WHERE type='table'")
tables = [row[0] for row in cursor.fetchall()]
print(f"Tables in database: {tables}")
# Check if usage_summaries exists
if "usage_summaries" not in tables:
print("usage_summaries table doesn't exist. Creating it...")
create_usage_summaries_table(cursor)
conn.commit()
conn.close()
print("Done! Table created successfully.")
return
# Get existing columns
cursor.execute("PRAGMA table_info(usage_summaries)")
existing_columns = {row[1] for row in cursor.fetchall()}
print(f"Existing columns in usage_summaries: {len(existing_columns)}")
# Columns to add (name, type, default)
columns_to_add = [
# Call counts
("wavespeed_calls", "INTEGER", "0"),
("tavily_calls", "INTEGER", "0"),
("serper_calls", "INTEGER", "0"),
("metaphor_calls", "INTEGER", "0"),
("firecrawl_calls", "INTEGER", "0"),
("stability_calls", "INTEGER", "0"),
("exa_calls", "INTEGER", "0"),
("video_calls", "INTEGER", "0"),
("image_edit_calls", "INTEGER", "0"),
("audio_calls", "INTEGER", "0"),
# Token usage
("wavespeed_tokens", "INTEGER", "0"),
# Cost tracking
("wavespeed_cost", "REAL", "0.0"),
("tavily_cost", "REAL", "0.0"),
("serper_cost", "REAL", "0.0"),
("metaphor_cost", "REAL", "0.0"),
("firecrawl_cost", "REAL", "0.0"),
("stability_cost", "REAL", "0.0"),
("exa_cost", "REAL", "0.0"),
("video_cost", "REAL", "0.0"),
("image_edit_cost", "REAL", "0.0"),
("audio_cost", "REAL", "0.0"),
]
added = []
skipped = []
for col_name, col_type, default in columns_to_add:
if col_name in existing_columns:
skipped.append(col_name)
continue
try:
sql = f"ALTER TABLE usage_summaries ADD COLUMN {col_name} {col_type} DEFAULT {default}"
cursor.execute(sql)
added.append(col_name)
print(f" Added: {col_name}")
except sqlite3.Error as e:
print(f" Error adding {col_name}: {e}")
conn.commit()
conn.close()
print(f"\nSummary:")
print(f" Added: {len(added)} columns")
print(f" Skipped (already exist): {len(skipped)} columns")
if added:
print(f"\nColumns added: {', '.join(added)}")
if skipped:
print(f"Already existed: {', '.join(skipped)}")
if __name__ == "__main__":
add_missing_columns()

1
backend/emojis.txt Normal file
View File

@@ -0,0 +1 @@
{'🎙', '🛑', '🚀', '📖', '💳', '📈', '🌐', '📊', '📦', '🔧', '🔍'}

View File

@@ -0,0 +1,530 @@
# Audio-Only Podcast Optimization Plan
## Executive Summary
This document outlines the optimization strategy for audio-only podcasts in ALwrity's Podcast Maker. The goal is to maximize the character throughput per API request while maintaining cost efficiency and audio quality.
---
## 1. Current Cost Analysis
### 1.1 Pricing Structure
| Service | Provider | Cost Formula | Notes |
|---------|----------|--------------|-------|
| **TTS (Audio)** | Minimax Speech-02-HD (WaveSpeed) | $0.05 per 1,000 chars | Exact billing per character |
| **Voice Clone** | Minimax Voice Clone | $0.50 per clone | One-time if using custom voice |
| **Research** | Exa Neural Search | $0.005 per query | + ~$0.001 for LLM insight extraction |
| **Avatar** | Ideogram Character | $0.10 per image | Only if AI-generated |
### 1.2 Cost Examples
| Podcast Duration | Characters (est.) | TTS Cost | Total Cost (audio-only) |
|------------------|-------------------|----------|--------------------------|
| 1 minute | 750 | $0.04 | $0.07 |
| 3 minutes | 2,250 | $0.11 | $0.14 |
| 5 minutes | 3,750 | $0.19 | $0.22 |
| 10 minutes | 7,500 | $0.38 | $0.41 |
---
## 2. Technical Constraints
### 2.1 API Limits
**Backend**: `main_audio_generation.py` (line 100)
```python
if len(text) > 10000:
raise ValueError(f"Text is too long ({len(text)} characters). Maximum is 10,000 characters.")
```
**Current Limit**: 10,000 characters per single API request
### 2.2 Scene-Based Architecture
- Each scene = 1 API call
- Default scene length: 45 seconds (`scene_length_target` knob)
- Audio is generated per scene, then concatenated
---
## 3. Optimization Strategies
### 3.1 Strategy 1: Fewer, Longer Scenes
**Problem**: More scenes = more API calls = higher costs
**Solution**:
- Increase `scene_length_target` from 45s to 60s or 90s
- Fewer scenes for the same podcast duration
**Impact**:
| Duration | Scenes (45s) | Scenes (60s) | Scenes (90s) | API Call Savings |
|----------|-------------|--------------|--------------|------------------|
| 5 min | 7 | 5 | 3 | 57% fewer calls |
| 10 min | 13 | 10 | 7 | 46% fewer calls |
### 3.2 Strategy 2: Per-Scene Character Budgeting
**Current behavior**: Each scene text is sent separately to TTS API
**Optimization options**:
1. **Text Concatenation**: Combine multiple scene texts with `<#x#>` pause markers
```python
# Example: Combine scenes with pause markers
combined_text = "Scene 1 text.<#x#>Scene 2 text.<#x#>Scene 3 text."
```
- Risk: May hit 10,000 char limit faster
- Benefit: Single API call for multiple scenes
2. **Smart Chunking**: Dynamically batch scenes based on character count
```python
MAX_CHARS_PER_REQUEST = 9500 # Leave buffer
# Group scenes until approaching limit
```
### 3.3 Strategy 3: Voice Settings for Longer Content
**Speed factor impacts**:
- Speed 0.8 = 25% more content per same duration
- Speed 1.2 = 20% less content
**Recommendation**: Use speed 0.9-1.0 for optimal quality/cost balance
### 3.4 Strategy 4: Audio-Only Mode Skip
**For audio-only podcasts** (no video):
1. **Skip avatar generation** - Save $0.10 per speaker
2. **Skip video rendering** - Save $0.30 per scene
3. **Skip scene images** - Save $0.04-$0.10 per scene
**Estimated savings for 5-min, 5-scene audio podcast**:
| Component | Cost | Audio-Only Savings |
|-----------|------|---------------------|
| Avatar | $0.10 | $0.10 |
| Video (5 scenes) | $1.50 | $1.50 |
| Images (5 scenes) | $0.20-$0.50 | $0.20-$0.50 |
| **Total** | $1.80-$2.10 | **$1.80-$2.10** |
---
## 4. Implementation Plan
### 4.1 Phase 1: User-Facing Controls (Frontend)
#### 4.1.1 Add "Audio Only" Toggle
- Location: `CreateModal.tsx` or `PodcastConfiguration.tsx`
- Options: `Audio Only` | `Video Only` | `Audio + Video`
- When enabled: Skip avatar, image, video generation
- Pass `audio_only: true` or `video_only: true` to backend
#### 4.1.2 Cost Preview Updates
- Show cost comparison based on selected mode
- Display potential savings for audio-only vs video
### 4.2 Phase 2: Script Editor UI (NEW - CRITICAL)
#### 4.2.1 Three Mode UI Strategy
The script editor needs to adapt based on the podcast mode:
| Mode | Script Editor UI | Available Actions |
|------|------------------|-------------------|
| **Audio Only** | Single audio-optimized script | Generate Audio only |
| **Video Only** | Current video script editor | Generate Audio + Image + Video |
| **Audio + Video** | Two tabs: "Audio Script" + "Video Script" | Full generation options |
#### 4.2.2 Implementation Details
**File:** `frontend/src/components/PodcastMaker/ScriptEditor/ScriptEditor.tsx`
**New Component Structure:**
```typescript
interface ScriptEditorProps {
// ... existing props
audioOnlyMode: boolean; // Audio-only podcast
videoOnlyMode: boolean; // Video-only podcast (current behavior)
audioScript?: Script; // Audio-optimized script (3-4 scenes, more lines)
videoScript?: Script; // Video-optimized script (current)
onAudioScriptChange?: (script: Script) => void;
onVideoScriptChange?: (script: Script) => void;
}
```
**UI Layout:**
```
┌─────────────────────────────────────────────────────────────┐
│ Script Editor [Audio] [Video] tabs (if both)
├─────────────────────────────────────────────────────────────┤
│ Mode: Audio-Only │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ Scene 1: Introduction (90s) [Edit]│ │
│ │ Host: Welcome to today's episode... │ │
│ │ Host: Today we're diving deep into... │ │
│ │ ... (6-10 lines per scene for audio) │ │
│ └─────────────────────────────────────────────────────┘ │
│ │
│ [Generate Audio] $0.04 │
└─────────────────────────────────────────────────────────────┘
```
#### 4.2.3 Tab Implementation for Audio + Video Mode
**When both Audio and Video are selected:**
1. Show two tabs in script editor:
- **Tab 1: "Audio Script"** - Audio-optimized (fewer scenes, more content)
- **Tab 2: "Video Script"** - Current video script (more scenes, visual)
2. Each tab has independent:
- Scene structure
- Edit capabilities
- Generation buttons
3. Generation actions differ by tab:
- Audio Tab: "Generate Audio" button only
- Video Tab: "Generate Audio" + "Generate Image" + "Generate Video"
#### 4.2.4 Backend Script Generation Updates
**Script generation endpoint changes:**
```python
# In PodcastScriptRequest model
class PodcastScriptRequest(BaseModel):
# ... existing fields
audio_only: bool = False # Generate audio-optimized script
video_only: bool = False # Generate video-optimized script (current)
# If both False AND audio/video mode is "both", generate both scripts
```
**Prompt Selection Logic:**
```python
if request.audio_only:
prompt = AUDIO_ONLY_PROMPT # 3-4 scenes, 6-10 lines/scene
elif request.video_only:
prompt = VIDEO_PROMPT # Current 5-6 scenes, 2-4 lines/scene
else:
# Generate both scripts with respective prompts
audio_prompt = AUDIO_ONLY_PROMPT
video_prompt = VIDEO_PROMPT
```
### 4.3 Phase 3: Backend Script Generation (AI Prompts)
#### 4.2.1 Two-Tier Script Generation Strategy
**Current Behavior (Video Podcast):**
- Existing prompt in `backend/api/podcast/handlers/script.py` (lines 125-151)
- Optimized for video with shorter scenes (2-4 lines per scene)
- 5-6 scenes max for visual storytelling
- Less content per scene to match video duration
**New Audio-Only Mode:**
- New prompt optimized for audio-only content
- More content-dense, information-rich
- Fewer scenes with MORE content per scene
- Maximizes use of research data
- Reduces API calls while delivering more value
#### 4.2.2 Audio-Only Script Prompt
**Location:** `backend/api/podcast/handlers/script.py`
**New Prompt for Audio-Only:**
```python
AUDIO_ONLY_PROMPT = """Create a DEEP, content-rich podcast script optimized for AUDIO-ONLY delivery.
{f"RESEARCH DATA (Use extensively - this is audio only, more content is better): {research_context[:3000]}" if research_context else "No research available - generate general content"}
{f"BIBLE: {bible_context[:1500]}" if bible_context else ""}
{f"{analysis_context}" if analysis_context else ""}
Topic: "{request.idea}"
Duration: {request.duration_minutes} min | Speakers: {request.speakers}
MODE: AUDIO-ONLY (no video constraints - maximize content density)
COST OPTIMIZATION (Audio-Only):
- 3-4 scenes MAX for entire episode (fewer scenes = fewer API calls)
- EACH scene should have 6-10 LINES (more content per scene)
- Each line: 3-5 sentences, information-dense
- Include: facts, statistics, examples, insights from research
- NO visual descriptions needed (save tokens for content)
- Make every line deliver unique value
STRUCTURE per scene:
- scene_id: string
- title: short descriptive title
- duration: seconds (target {request.duration_minutes*60 // 3}-{request.duration_minutes*60 // 4} per scene)
- emotion: neutral|happy|excited|serious|curious|confident
- lines: array of {{speaker, text, emphasis}}
- speaker: "Host" or "Guest"
- text: 3-5 sentences, rich with facts/insights
- emphasis: true|false for important points
Return JSON with scenes array.
"""
```
**Key Differences:**
| Aspect | Video (Current) | Audio-Only (New) |
|--------|------------------|------------------|
| Scenes | 5-6 | 3-4 |
| Lines/Scene | 2-4 | 6-10 |
| Sentences/Line | 1-3 | 3-5 |
| Research Usage | 1,200 chars | 3,000 chars |
| Focus | Visual storytelling | Content density |
| API Calls | More (lower cost/scene) | Fewer (higher cost/scene) |
#### 4.2.3 Implementation Details
**File:** `backend/api/podcast/handlers/script.py`
1. Add `audio_only: bool` parameter to `PodcastScriptRequest`
2. Conditionally select prompt based on `audio_only` flag
3. For audio-only:
- Use expanded research context (3,000 chars vs 1,200)
- Request more lines per scene
- Fewer total scenes
- More content per line
### 4.4 Phase 4: Backend Optimizations
#### 4.3.1 Smart Scene Batching
- File: `backend/api/podcast/handlers/audio.py`
- Logic: Group scenes with total chars < 9000
- Add pause markers between scenes
#### 4.3.2 Audio-Only Flag in Project
- Model: Add `audio_only: bool` to project settings
- Skip: Avatar generation, image generation, video rendering
### 4.4 Phase 4: Cost Calculation Updates
#### 4.4.1 Update Frontend Estimation
- File: `frontend/src/services/podcastApi.ts`
- Formula updates:
```typescript
const estimatedApiCalls = Math.ceil(totalChars / 9500);
const ttsCost = estimatedApiCalls * 0.05;
```
---
## 5. Technical Details
### 5.1 Files to Modify
| File | Changes |
|------|---------|
| `frontend/src/components/PodcastMaker/types.ts` | Add `audio_only`, `video_only`, `podcast_mode` to project settings |
| `frontend/src/components/PodcastMaker/CreateModal.tsx` | Add mode toggle (Audio/Video/Both) |
| `frontend/src/services/podcastApi.ts` | Update cost estimation for each mode |
| `frontend/src/components/PodcastMaker/ScriptEditor/ScriptEditor.tsx` | Add tab support for Audio + Video mode |
| `frontend/src/components/PodcastMaker/ScriptEditor/SceneEditor.tsx` | Conditional action buttons per mode |
| `backend/api/podcast/models.py` | Add `audio_only`, `video_only` fields to request model |
| `backend/api/podcast/handlers/script.py` | Add audio-only + video-only prompts, return both scripts when needed |
| `backend/api/podcast/handlers/audio.py` | Implement smart batching |
### 5.2 API Endpoints
```python
# PodcastScriptRequest model changes
class PodcastScriptRequest(BaseModel):
idea: str
duration_minutes: int
speakers: int
research: Optional[Dict] = None
bible: Optional[Dict] = None
analysis: Optional[Dict] = None
outline: Optional[Dict] = None
# NEW FIELDS:
audio_only: bool = False # Generate audio-optimized script
video_only: bool = False # Generate video-optimized script (current)
# Both False = generate both scripts for audio+video mode
# Response includes both scripts when needed
class PodcastScriptResponse(BaseModel):
audio_script: Optional[Script] = None # Audio-optimized
video_script: Optional[Script] = None # Video-optimized
```
### 5.3 Database Schema
```python
# In PodcastProject model
audio_only: bool = False
scene_length_target: int = 60 # seconds
```
---
## 6. User Experience
### 6.1 Create Phase - Mode Toggle
```
┌─────────────────────────────────────────────────────────────┐
│ 🎙️ Create New Podcast │
├─────────────────────────────────────────────────────────────┤
│ Duration: [5] minutes Speakers: [1] [2] │
│ │
│ Podcast Mode: │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ Audio Only │ │ Video Only │ │ Audio+Video │ │
│ │ ($0.22) │ │ ($2.02) │ │ ($2.24) │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
│ │
│ Est. Cost: $0.22 (audio only) vs $2.02 (with video) │
└─────────────────────────────────────────────────────────────┘
```
### 6.2 Script Editor - Audio Only Mode
```
┌─────────────────────────────────────────────────────────────┐
│ Script Editor │
├─────────────────────────────────────────────────────────────┤
│ 📻 Audio-Only Mode │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ Scene 1: Introduction (90s) [Edit]│
│ │ Host: Welcome to today's episode on AI... │
│ │ Host: Today we're diving deep into how AI... │
│ │ Host: I'm excited to share three key insights... │
│ │ ... (6-10 lines for audio) │
│ │ │
│ │ Scene 2: Main Topic (120s) [Edit]│
│ │ ... │
│ └─────────────────────────────────────────────────────┘ │
│ │
│ [Generate Audio] $0.04 [Generate Image] Disabled │
│ [Generate Video] Disabled │
└─────────────────────────────────────────────────────────────┘
```
### 6.3 Script Editor - Video Only Mode (Current)
```
┌─────────────────────────────────────────────────────────────┐
│ Script Editor │
├─────────────────────────────────────────────────────────────┤
│ 🎬 Video Mode │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ Scene 1: Intro (30s) [Image] [Audio] [V] │
│ │ Scene 2: Hook (30s) [Image] [Audio] [V] │
│ │ Scene 3: Content (45s) [Image] [Audio] [V] │
│ │ Scene 4: Example (30s) [Image] [Audio] [V] │
│ │ Scene 5: CTA (15s) [Image] [Audio] [V] │
│ └─────────────────────────────────────────────────────┘ │
│ │
│ [Generate Audio] $0.19 [Generate Image] $0.10 │
│ [Generate Video] $1.50 │
└─────────────────────────────────────────────────────────────┘
```
### 6.4 Script Editor - Audio + Video Mode (Both)
```
┌─────────────────────────────────────────────────────────────┐
│ Script Editor [Audio] [Video] │
├─────────────────────────────────────────────────────────────┤
│ ┌─────────────────────────────────────────────────────┐ │
│ │ [Audio] Tab | [Video] Tab │ │
│ ├─────────────────────────────────────────────────────┤ │
│ │ Audio Script: │ │
│ │ Scene 1: Intro (90s) - 8 lines │ │
│ │ Scene 2: Deep Dive (120s) - 10 lines │ │
│ │ │ │
│ │ [Generate Audio] $0.04 │ │
│ └─────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
OR
┌─────────────────────────────────────────────────────────────┐
│ Script Editor [Audio] [Video] │
├─────────────────────────────────────────────────────────────┤
│ ┌─────────────────────────────────────────────────────┐ │
│ │ [Audio] Tab | [Video] Tab │ │
│ ├─────────────────────────────────────────────────────┤ │
│ │ Video Script: │ │
│ │ Scene 1: Intro (30s) [Img] [Aud] [Vid] │ │
│ │ Scene 2: Hook (30s) [Img] [Aud] [Vid] │ │
│ │ Scene 3: Content (45s) [Img] [Aud] [Vid] │ │
│ │ │ │
│ │ [Generate Audio] [Generate Image] [Generate Video] │ │
│ └─────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
```
### 6.5 Cost Comparison UI
| Mode | Scenes | Lines/Scene | TTS Cost | Video Cost | Total |
|------|--------|-------------|----------|------------|-------|
| Audio Only | 3-4 | 6-10 | $0.19 | $0 | **$0.22** |
| Video Only | 5-6 | 2-4 | $0.19 | $1.50 | **$1.69** |
| Audio+Video | 3-4 + 5-6 | varies | $0.19 | $1.50 | **$1.72** |
---
## 7. Testing Plan
### 7.1 Unit Tests
1. Test character count calculation
2. Test scene batching logic (under 10k chars)
3. Test cost estimation accuracy
### 7.2 Integration Tests
1. Generate audio for 10-minute podcast with 5 scenes
2. Verify all scenes generate correctly
3. Verify cost tracking in database
### 7.3 Performance Tests
1. Measure time for batched vs sequential API calls
2. Verify no timeout issues with longer text
---
## 8. Success Metrics
| Metric | Target | Current |
|--------|--------|---------|
| API calls per 5-min podcast | 5 | 7 |
| Cost per 5-min audio podcast | $0.22 | $0.22 + video |
| User-visible savings | 50%+ | N/A |
| Scene length default | 60s | 45s |
---
## 9. Appendix: Related Files
### Backend
- `backend/services/llm_providers/main_audio_generation.py` - TTS cost calculation
- `backend/api/podcast/handlers/audio.py` - Audio generation endpoint
- `backend/api/podcast/handlers/script.py` - Script generation
- `backend/services/subscription/pricing_service.py` - Pricing configuration
### Frontend
- `frontend/src/services/podcastApi.ts` - Cost estimation
- `frontend/src/components/PodcastMaker/CreateModal.tsx` - Create UI
- `frontend/src/components/PodcastMaker/types.ts` - Type definitions
---
## Document History
| Version | Date | Author | Changes |
|---------|------|--------|---------|
| 1.0 | 2026-04-08 | ALwrity Team | Initial document creation |
---
*This document serves as the reference for audio-only podcast optimization in ALwrity Podcast Maker.*