- Reorder workflow: translations now happen BEFORE QC Review step
- Add language tabs to switch between translated languages in QC
- Add video mode tabs (Original Video / Accessible Video)
- Add interactive timeline preview showing video segments and AD cues
- Enable pause point adjustment with millisecond precision
- Add TTS regeneration queue for selective cue re-synthesis
- Add re-render controls with optional Whisper refinement
- Persist video segments and TTS MP3s to GCS for editability
- Add new RENDERING_QC job status for re-render operations
- Create 5 new API endpoints for accessible video editing
- Add rerender_accessible_video.py Celery task
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Subtitles were appearing progressively out of sync (~1.0s early per AD)
because the VTT retimer calculated freeze durations theoretically
rather than using actual rendered segment durations.
Changes:
- video_renderer: Measure actual freeze segment duration after creation
- video_renderer: Return updated placements with actual_freeze_duration
- vtt_retimer: Prefer actual_freeze_duration over calculated values
- render_task: Pass actual durations to VTT retimer
This ensures subtitle timing matches the real video timeline regardless
of any FFmpeg encoding variations.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When TTS synthesis fails after 3 retries, the system now:
- Sends problematic cue text to Gemini for TTS-safe rewriting
- Updates the VTT file in GCS with rewritten text
- Retries TTS synthesis with the new text
- Records successful rewrites in job.tts_rewrites field
UI changes:
- JobDetail shows amber caution box with original/rewritten text
- JobsList shows warning icon next to jobs with rewrites
- Error display clarifies text shown is "after rewrite attempt"
Files changed:
- backend/app/models/job.py: Add tts_rewrites field
- backend/app/prompts/gemini_tts_rewrite.md: New prompt template
- backend/app/services/gemini.py: Add rewrite_tts_cue method
- backend/app/tasks/tts_synthesis.py: Add VTT update utilities
- backend/app/tasks/translate_and_synthesize.py: Rewrite+retry logic
- frontend/src/types/api.ts: Add TTSRewriteItem type
- frontend/src/routes/jobs/JobDetail.tsx: Caution display
- frontend/src/routes/jobs/JobsList.tsx: Warning indicator
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The TTS error handling had a bug where failed jobs stayed in
'tts_generating' status instead of being set to 'tts_failed'.
Root cause: synthesize_cue_task used autoretry_for=(Exception,)
which raises the original exception after max retries, not
MaxRetriesExceededError. The exception handler never fired.
Changes:
- tts_synthesis.py: Replace autoretry_for with manual retry logic
that returns a failure dict on final failure instead of raising
- translate_and_synthesize.py: Add propagate=False to group.get()
to safely retrieve all results including failures
- translate_and_synthesize.py: Update outer exception handler to
set job status to tts_failed, store error details, and broadcast
status update via WebSocket
Now TTS failures will:
1. Set job status to 'tts_failed'
2. Store detailed error info (cue index, text, message)
3. Show error in UI with retry button
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Optimize the accessible video workflow by eliminating the dedicated
Gemini video analysis call for pause point estimation. Instead:
- Use AD VTT cue start times as initial pause points for Whisper refinement
- Add user-selectable accessible video method (pause_insert/overlay) at QC approval
- Add bulk approval API endpoint with method selection
- Add method selector UI to QCDetail page
- Add bulk approval modal to QCList for jobs with accessible video
Benefits:
- Eliminates expensive Gemini API call with video upload
- Faster workflow (~5-15 seconds saved per job)
- Cost savings on Gemini video analysis
- User control over accessible video integration method
Backend changes:
- Add accessible_video_method to RequestedOutputs and ApproveSourceRequest
- Add POST /jobs/bulk/approve endpoint
- Replace Gemini call with _build_placements_from_ad_vtt() helper
- Mark analyze_accessible_video_placement() as deprecated
Frontend changes:
- Add method selector radio buttons to QCDetail
- Add bulk approval modal with method selection to QCList
- Update API client and React Query hooks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Cloud Run services are deployed with --no-allow-unauthenticated,
requiring an ID token in the Authorization header.
- Add _get_cloud_run_id_token() helper using google-auth library
- Update whisper_transcribe.py to include Bearer token in Cloud Run calls
- Update video_renderer.py to include Bearer token in FFmpeg Cloud Run calls
The ID token is fetched using the service account credentials
(GOOGLE_APPLICATION_CREDENTIALS) and targets the Cloud Run service URL.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Migrate CPU-intensive workloads to Cloud Run for autoscaling:
- Add Whisper HTTP service (FastAPI) with /transcribe endpoint
- Add FFmpeg HTTP service (FastAPI) with /encode, /probe, /extract-frame, etc.
- Add Dockerfiles for both services (8 vCPU, 32GB RAM, Gen2)
- Add Cloud Build config for CI/CD deployment
- Add Cloud Run service YAML configs with scale-to-zero
- Update whisper_transcribe.py to call Cloud Run when WHISPER_SERVICE_URL set
- Update video_renderer.py to call Cloud Run when FFMPEG_SERVICE_URL set
- Update whisper_service.py for Cloud Run compatibility (no settings dependency)
- Add ffmpeg_service_url and whisper_service_url to config.py
Services scale 0→N based on request load, falling back to local
execution when service URLs are not configured (hybrid mode).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add RENDER_FAILED job status for when video rendering fails
- Fix _check_accessible_video_completion to detect failures and transition
job status accordingly (was stuck in RENDERING_VIDEO forever)
- Store detailed error info in job.error including failed_languages array
- Call completion check after failures to properly update job status
- Broadcast WebSocket notification on render failures
Frontend:
- Add render_failed to JobStatus type and StatusBadge (red styling)
- Add tts_failed and render_failed to JobsList STATUS_LABELS
- Enhance JobDetail error display with:
- Warning icon and prominent styling
- Error type and message
- Failed languages list with per-language errors
- Timestamp of when error occurred
- Update ProgressIndicator to handle failed states with red dot
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Video-native translation mode now processes all target languages in parallel
using asyncio.gather() with a semaphore (max 3 concurrent) for rate limiting.
This significantly reduces total translation time when multiple languages
are selected.
- Add MAX_CONCURRENT_VIDEO_NATIVE constant for rate limiting
- Refactor video-native path to use parallel coroutines
- Keep traditional VTT translation mode sequential
- Handle per-language errors without stopping other translations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a new "Video Native Mode" translation option that re-processes the
video through Gemini for each target language, generating captions and
audio descriptions directly from visual context. This produces more
natural and culturally appropriate content compared to traditional VTT
text translation.
Changes:
- Add translation_mode field to RequestedOutputs (video_native | traditional)
- Create gemini_ingestion_targeted.md prompt for target language generation
- Add extract_accessibility_targeted() method to Gemini service
- Modify translate_and_synthesize task to handle both translation modes
- Add Translation Mode UI selector in NewJob screen (video_native is default)
- Remove transcreation UI (replaced by video_native mode)
- Remove Google Translate service (replaced by Gemini translation)
- Add LanguageSelector component with searchable dropdown
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Break out TTS synthesis into a dedicated Celery worker (tts queue) with
concurrency=8 for parallel processing. Each AD cue is now synthesized as
a separate task, enabling up to 8 cues to be processed simultaneously.
Key changes:
- Add tts_synthesis.py with synthesize_cue_task for per-cue synthesis
- Refactor translate_and_synthesize.py to dispatch cue tasks in parallel
- Add tts-worker service to docker-compose.yml (concurrency=8)
- Add Cloud Run service config for production deployment
Benefits:
- Parallel synthesis even for single jobs (e.g., 50 cues → 8 concurrent)
- Natural rate limiting across multiple concurrent jobs
- Fault tolerance with per-cue retries and GCS persistence
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Completely rewrites the Whisper-based pause point refinement to use
a two-phase approach with explicit ordering:
Phase 1 - Individual refinement:
1. Check if pause point is "during speaking" (words within ±2s)
- If NOT during speaking → use Gemini's exact point, no overlap
2. If during speaking, find nearest sentence boundary
3. Apply appropriate buffering based on context:
- Case A: First sentence → pause 500ms before sentence starts
- Case B: Last sentence → pause 500ms after sentence ends
- Case C: Between sentences → full double buffer (overlap)
Phase 2 - Consolidation (after all refinements):
- Consolidate cues within 5s of each other to play back-to-back
Key changes:
- Add SentenceBoundary dataclass for tracking boundaries with context
- Add _is_during_speaking() helper to detect speech proximity
- Add _find_sentence_boundaries() with longest-gap fallback
- Rewrite snap_pause_point() with new ordered algorithm
- Update refine_all_pause_points() to pass words and use two phases
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove the cached transcript lookup - always run a fresh Whisper
transcription for each accessible video render. This ensures we get
accurate word timestamps for the current video file.
The transcript is still saved to the job document for debugging and
auditing purposes, but it will never be read back for reuse.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changed the Whisper transcription to run on dedicated whisper-worker
using the same dispatch pattern as FFmpeg:
1. apply_async() to dispatch to the whisper queue
2. Poll with ready() using async sleep to avoid blocking
3. Use allow_join_result() context manager
4. Get result only after task is ready
This ensures Whisper runs with concurrency=1 on a dedicated worker
to prevent memory overload while still allowing the render task
to wait for results without deadlocking.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Celery does not allow calling result.get() within a task as it causes
deadlocks. Changed the implementation to run Whisper transcription
directly using asyncio.to_thread() instead of dispatching to a separate
Celery queue.
The Whisper transcript is still cached in MongoDB for reuse across
language variants.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements word-level speech analysis using faster-whisper to refine
AD pause points. Gemini's timestamps are snapped to natural speech gaps
(sentence/phrase boundaries) to prevent pauses mid-word.
Key changes:
- Add WhisperService for transcription and gap detection
- Add dedicated Celery task routed to 'whisper' queue
- Integrate refinement into render_accessible_video task
- Cache Whisper transcripts in MongoDB for reuse across languages
- Add dedicated whisper-worker with concurrency=1 to prevent OOM
Configuration:
- Uses faster-whisper 'base' model (multilingual, ~145MB)
- 5-second search window after Gemini's recommended point
- Falls back to original timestamp if no gap found
Infrastructure:
- New Docker stage: whisper-worker
- New Cloud Run service: accessible-video-whisper-worker
- Updated docker-compose.yml with whisper-worker service
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously only the final pending_qc status was broadcast via WebSocket.
Now all intermediate status changes (ingesting, ai_processing) are also
broadcast so the frontend can update in real-time during reprocessing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When jobs with accessible video option enabled enter video rendering
phase, the status now transitions to 'rendering_video' so users can
see why processing is taking longer. This provides better visibility
into the video rendering pipeline.
Changes:
- Added RENDERING_VIDEO status to JobStatus enum
- Updated render_accessible_video task to set new status
- Added status display to StatusBadge, jobStatusMessages
- Included new status in JobsList Translation filter group
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Modified render_accessible_video.py to explicitly pass TMPDIR to
tempfile.TemporaryDirectory() so files are created in shared volume
- Updated docker-compose.yml to run containers as root initially,
chown /shared-tmp to app:app, then switch to app user for celery
- This ensures both worker containers can access the same temp files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a dedicated Celery queue (ffmpeg) with concurrency=1 to serialize
all FFmpeg operations. This prevents CPU spikes when multiple render
tasks run in parallel with multiple languages.
Changes:
- Add ffmpeg_operations.py with run_ffmpeg_command and run_ffprobe_command tasks
- Update VideoRendererService to dispatch ffmpeg commands via the queue
- Add ffmpeg-worker service to docker-compose with --concurrency=1
- Configure main worker to exclude the ffmpeg queue
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new deliverable type that renders video with audio descriptions embedded.
Supports two AI-determined methods:
- Direct Overlay: ducks original audio and overlays AD TTS (for minimal dialogue)
- Pause-Insert: freeze-frame video, insert AD, re-time subtitles (for significant dialogue)
Backend:
- Add Pydantic schemas for Gemini analysis response
- Add Gemini prompt and analyze_accessible_video_placement() method
- Add video_renderer.py service using FFmpeg for both rendering methods
- Add vtt_retimer.py service for pause-insert subtitle adjustment
- Add render_accessible_video.py Celery task
- Modify TTS service to return individual per-cue segments
- Update translate_and_synthesize.py to save segments and trigger rendering
- Update download endpoint to include accessible video outputs
Frontend:
- Add accessible_video_mp4 checkbox to NewJob form
- Update TypeScript types for new deliverable
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add model selection (flash vs pro) for quality control
- Add speed slider (0.5x - 2.0x) for pacing adjustment
- Add style presets (neutral, calm, energetic, professional, warm, documentary)
- Add custom style prompt option for advanced customization
- New /tts/options endpoint returns available TTS options
- Voice preview now tests all settings so users hear exact output
- Backward compatible: all new fields have sensible defaults
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Gemini TTS service with 30 voices and 24 languages
- Add TTS API endpoints for voice listing and preview
- Add per-language voice selection in job creation form
- Add voice override at QC approval stage
- Add VoiceSelector and VoicePreviewButton components
- Update TTSPreferences model with provider and voice mapping
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Upload form now has "English / Different language" radio with optional language hint
- Gemini auto-detects language and saves outputs to outputs.{detected_language}
- QC review dynamically loads/saves VTT for source language
- New APPROVED_SOURCE status for non-English videos (APPROVED_ENGLISH kept for backwards compat)
- Translation pipeline reads from source language and passes source_language to Google Translate
- All existing English jobs continue to work unchanged
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
