feat: voice clone audio generation + podcast workspace architecture

- Voice clone integration: When user selects voice clone in Write phase,
  backend uses their uploaded voice sample + scene script text to generate
  audio via qwen3/minimax/cosyvoice voice clone APIs
- Multi-tenant workspace storage: All podcast assets (audio, video, images,
  charts) now use workspace-specific directories per user
- Chart preview improvements: Card-based B-Roll charts UI with thumbnails,
  takeaway text, and action buttons; public endpoint for image serving
- Voice clone caching: In-memory LRU cache for voice samples (avoids
  re-downloading per scene); frontend caches voice clone metadata
- Thread pool for voice clone: Audio generation uses ThreadPoolExecutor to
  avoid blocking the FastAPI event loop
- Auto-detect voice clone IDs (vc_*, MY_VOICE_CLONE) to route correctly
- DB fallback for voice sample URL: Fetches from ContentAsset if not passed
- Fixed API URL resolution for chart previews
- Fixed GlassyCard DOM warnings for motion props
- Fixed ScriptGenerationProgressView syntax error
- Fixed usePodcastWorkflow scriptData reference
This commit is contained in:
ajaysi
2026-04-21 19:38:50 +05:30
parent 7637babd7d
commit 91b2f996fd
33 changed files with 1642 additions and 457 deletions

View File

@@ -93,9 +93,14 @@ billingAPI.interceptors.response.use(
async (error) => {
const originalRequest = error.config;
// Handle network errors
// Handle network errors - but NOT timeouts (backend might just be slow)
if (!error.response) {
noteBackendUnavailable(error?.message || 'billing_network_error');
const errorMsg = error?.message || '';
const isTimeout = errorMsg.includes('timeout') || errorMsg.includes('ETIMEDOUT');
if (!isTimeout) {
noteBackendUnavailable(errorMsg || 'billing_network_error');
}
console.error('Billing API Network Error:', error.message);
return Promise.reject(error);
}

View File

@@ -1,3 +1,4 @@
import { noteBackendRecovered } from "../api/client";
import { ResearchProvider, ResearchConfig } from "./blogWriterApi";
import {
storyWriterApi,
@@ -28,12 +29,42 @@ const DEFAULT_KNOBS: Knobs = {
voice_speed: 1,
voice_id: "Wise_Woman",
custom_voice_id: undefined,
is_voice_clone: undefined,
voice_sample_url: undefined,
voice_clone_engine: undefined,
resolution: "720p",
scene_length_target: 45,
sample_rate: 24000,
bitrate: "standard",
};
// In-memory cache for voice clone info to avoid re-fetching per scene
let _voiceCloneCache: {
customVoiceId?: string;
voiceSampleUrl?: string;
engine?: string;
isVoiceClone?: boolean;
timestamp: number;
} | null = null;
const VOICE_CLONE_CACHE_TTL = 30 * 60 * 1000; // 30 minutes
export function getCachedVoiceCloneInfo() {
if (_voiceCloneCache && Date.now() - _voiceCloneCache.timestamp < VOICE_CLONE_CACHE_TTL) {
return _voiceCloneCache;
}
_voiceCloneCache = null;
return null;
}
export function setCachedVoiceCloneInfo(info: {
customVoiceId?: string;
voiceSampleUrl?: string;
engine?: string;
isVoiceClone?: boolean;
}) {
_voiceCloneCache = { ...info, timestamp: Date.now() };
}
// const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
const createId = (prefix: string) => {
@@ -244,9 +275,9 @@ const mapExaResearchResponse = (response: any): Research => {
};
const ensurePreflight = async (operation: PreflightOperation) => {
console.log('[podcastApi] Running preflight for:', operation);
console.log('[podcastApi] Running preflight for:', operation.operation_type);
const result = await checkPreflight(operation);
console.log('[podcastApi] Preflight result:', result);
console.log('[podcastApi] Preflight result: can_proceed=', result.can_proceed);
if (!result.can_proceed) {
const message = result.operations[0]?.message || "Pre-flight validation failed";
throw new Error(message);
@@ -379,7 +410,9 @@ export const podcastApi = {
bible: params.bible,
analysis: params.analysis,
}, { timeout: 300000 }); // 5 minute timeout for research
console.log('[podcastApi] Exa research response received:', response.status, response.data);
const sourceCount = response.data?.sources?.length || 0;
const insightCount = response.data?.key_insights?.length || 0;
console.log(`[podcastApi] Exa research response: status=${response.status}, sources=${sourceCount}, insights=${insightCount}`);
} catch (error: any) {
console.error('[podcastApi] Exa research error:', error?.response?.status, error?.response?.data, error?.message);
throw error;
@@ -497,6 +530,9 @@ export const podcastApi = {
scene: Scene;
voiceId?: string;
customVoiceId?: string;
useVoiceClone?: boolean;
voiceSampleUrl?: string;
voiceCloneEngine?: string;
emotion?: string; // Fallback if scene doesn't have emotion
speed?: number;
volume?: number;
@@ -600,7 +636,7 @@ export const podcastApi = {
channel: params.channel || null,
format: params.format || null,
language_boost: params.languageBoost || null,
});
}, { timeout: 300000 }); // 5 minute timeout for voice clone / TTS
return {
audioUrl: response.data.audio_url,
@@ -623,12 +659,14 @@ export const podcastApi = {
},
// Project persistence endpoints
async saveProject(projectId: string, state: any): Promise<void> {
async saveProject(projectId: string, state: any): Promise<boolean> {
try {
await aiApiClient.put(`/api/podcast/projects/${projectId}`, state);
return true;
} catch (error) {
console.error("Failed to save project to database:", error);
// Don't throw - localStorage fallback is acceptable
noteBackendRecovered();
return false;
}
},
@@ -952,6 +990,9 @@ export const podcastApi = {
scenes: { id: string; title: string; lines: { text: string }[] }[];
voiceId: string;
customVoiceId?: string;
useVoiceClone?: boolean;
voiceSampleUrl?: string;
voiceCloneEngine?: string;
speed: number;
emotion: string;
englishNormalization?: boolean;