video-accessibility/backend/app
michael dad7ea09df fix: generate audio descriptions in the video's detected language
Updated Gemini ingestion prompt to explicitly require:
- Detect the spoken language first
- Write ALL outputs (summary, transcript, captions, audio_description) in that language
- Do NOT translate to English - keep everything in the original language

This fixes the issue where German videos would get English audio descriptions.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-22 19:01:14 -06:00
..
__pycache__ fixed middleware silent swallowing of exceptions FINALLY 2025-10-08 18:19:59 -05:00
api/v1 feat: add TTS settings panel with model, speed, and style options 2025-12-22 15:22:14 -06:00
core feat: add TTS settings panel with model, speed, and style options 2025-12-22 15:22:14 -06:00
lib initial commit 2025-08-24 16:28:33 -05:00
middleware fixed overly aggressive security algorithm 2025-10-08 17:49:20 -05:00
migrations add approved_source and qc_feedback job statuses to MongoDB schema 2025-12-22 13:12:14 -06:00
models feat: add TTS settings panel with model, speed, and style options 2025-12-22 15:22:14 -06:00
prompts fix: generate audio descriptions in the video's detected language 2025-12-22 19:01:14 -06:00
schemas upgrade TTS to Gemini TTS with voice selection and preview 2025-12-22 14:41:57 -06:00
services feat: add TTS settings panel with model, speed, and style options 2025-12-22 15:22:14 -06:00
tasks feat: add TTS settings panel with model, speed, and style options 2025-12-22 15:22:14 -06:00
telemetry initial commit 2025-08-24 16:28:33 -05:00
main.py upgrade TTS to Gemini TTS with voice selection and preview 2025-12-22 14:41:57 -06:00