- Skip onboarding in demo mode, redirect to podcast-maker
- Demo mode checks localStorage and env vars
- Remove mock subscription - use real subscription flow
- Add demoMode utility for consistent demo mode detection
- Skip onboarding API calls in OnboardingContext when in demo mode
- Redirect to /podcast-maker instead of /onboarding in demo mode
- Patch pricing redirect to route to podcast-maker instead of onboarding
- Allow all plan tiers in demo mode (remove alpha restriction)
- Add Stripe mode warning in demo when key is missing
- Add startup router mount assertions for subscription and podcast
- Add smoke test script for demo mode validation
- Add dedicated image_generation module with statistical extraction
- Support 16 industry domains with visual concept detection
- Add model-specific guidance for Ideogram, FLUX, GLM, Qwen, MAI
- Extract statistics, rankings, comparisons, and trends automatically
- Refactor backend/api/images.py to use new module
This commit adds the Auto-Dubbing feature for Podcast Maker with support
for translating podcast audio to different languages with optional voice
cloning to preserve the original speaker's voice.
New Features:
- Translation Service (common module): DeepL integration for low-cost
translation, WaveSpeed integration for high-quality translation
- Audio Dubbing Service: STT -> Translate -> TTS pipeline with
voice cloning support
- 9 new API endpoints for dubbing and voice cloning
- Support for 34+ languages
- Cost estimation utilities
- Comprehensive documentation
Files Added:
- services/translation/ (5 files): Translation service module
- services/dubbing/: Audio dubbing service
- api/podcast/handlers/dubbing.py: API endpoints
- docs/AUTO_DUBBING.md: Feature documentation
- CHANGELOG.md: Change log
Files Modified:
- api/podcast/models.py: Added dubbing request/response models
- api/podcast/router.py: Added dubbing routes
- services/__init__.py: Export translation and dubbing services
- scene_animation.py: Fixed missing Path import
New tools added to ToBeMigrated/ directory:
ai_marketing_tools/:
- ai_backlinker: AI-powered backlink generation
- ai_google_ads_generator: Google Ads generation with templates
ai_writers/:
- ai_blog_faqs_writer: FAQ generation for blogs
- ai_copywriter: Multiple copywriter frameworks (AIDA, PAS, 4C, 4R, etc.)
- ai_finance_report_generator: Financial report generation
- ai_story_illustrator: Story illustration
- ai_story_video_generator: Story video generation
- ai_story_writer: AI story writing
- github_blogs: GitHub blog integration
- speech_to_blog: Audio to blog conversion
- twitter_writers: Twitter/X content generation
- youtube_writers: YouTube content generation
These tools are in ToBeMigrated/ for future migration to the main backend.
- Add services/startup_health.py with health check functions:
- get_startup_status(): Returns current startup status
- readiness_under_auth_context(): Validates tenant DB under auth context
- run_startup_health_routine(): Runs all startup health checks
- Add /health/readiness endpoint for tenant DB validation
- Update startup_event() to use run_startup_health_routine()
- Add raise to startup_event to fail fast on errors
- Remove dependency on workspace_dirs module
- Use direct Path().mkdir() for directory creation
- Configure development directories correctly (lib/workspace/...)
- Skip directory creation in production mode
New models for managing content strategy runtime state:
- StrategyGenerationTaskState: Task lifecycle/status for polling-based AI generation
- LatestGeneratedStrategyState: References to latest generated strategy per user/resource
- StreamingCacheState: Short-lived streaming cache entries with TTL semantics
These models provide persistent state management for content strategy operations.
- Import APIKeyManager for provider key checking
- Use APIKeyManager.get_api_key() instead of get_api_key() function
- Add wavespeed provider to available_providers check
- Add detailed provider preflight logging with flow_type tag
- Improve fallback logic when preferred provider is unavailable
These improvements come from PRs #423-#431 while maintaining the modular textgen_utils structure.
huggingface_provider.py:
- Add retry logic with _should_retry_hf_error and _is_non_retryable_hf_error
- Update default models from :groq to :cerebras (HF_FALLBACK_MODELS)
- Add fallback_models parameter to huggingface_text_response
- Add get_available_models with updated model list
main_text_generation.py:
- Add GPT_PROVIDER and TEXTGEN_AI_MODELS env var support
- Add preferred_provider and flow_type parameters to llm_text_gen
- Add HF_MODEL_MAPPING for short model name resolution
- Add flow_type logging tag for better observability
sif_agents.py:
- Add LOW_COST_SHARED_REMOTE_MODELS for SIF agents
- Update SharedLLMWrapper to use preferred_hf_models and flow_type
These changes preserve the modular textgen_utils structure while incorporating
the useful routing and retry logic improvements from the pending PRs.
- Add get_current_user authentication to all user data endpoints
- Pass authenticated user_id from auth context to service methods
- Add proper HTTPException handling for missing data
- Fix user_id type from int to str in service methods
- Ensure endpoints only return data for authenticated user
- Add InterceptHandler to route stdlib logging to Loguru
- Add _patch_record_context for request/job/user ID tracking
- Add _uncaught_exception_hook to capture top-level exceptions
- Add _asyncio_exception_handler for asyncio task exceptions
- Add _register_global_exception_handlers to register all hooks
- Add _configure_uvicorn_loggers for unified uvicorn logging
- Improve log format with contextual fields (req, job, user)
