egg/Meeting_Assistant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: Archive add-dify-audio-transcription proposal

Browse Source 
Move completed Dify audio transcription proposal to archive and update
transcription spec with new capabilities.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
egg
2025-12-11 21:05:01 +08:00
parent 263eb1c394
commit 2e78e3760a
5 changed files with 435 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
openspec/changes/archive/2025-12-11-add-dify-audio-transcription/tasks.md Normal file
View File

@@ -0,0 +1,47 @@
# Implementation Tasks
## 1. Backend Configuration
- [x] 1.1 Add `DIFY_STT_API_KEY` to `backend/app/config.py`
- [x] 1.2 Add `DIFY_STT_API_KEY` to `backend/.env.example`
## 2. Sidecar VAD Segmentation
- [x] 2.1 Add `segment_audio` action handler in `sidecar/transcriber.py`
- [x] 2.2 Implement VAD-based audio segmentation using Silero VAD
- [x] 2.3 Support max chunk duration (default 5 minutes)
- [x] 2.4 Support minimum silence threshold (default 500ms)
- [x] 2.5 Export chunks as WAV files to temp directory
- [x] 2.6 Return segment metadata (paths, timestamps)
## 3. Backend API Endpoint
- [x] 3.1 Create `POST /api/ai/transcribe-audio` endpoint in `backend/app/routers/ai.py`
- [x] 3.2 Implement multipart file upload handling (max 500MB)
- [x] 3.3 Validate audio file format (MP3, WAV, M4A, WebM, OGG)
- [x] 3.4 Save uploaded file to temp directory
- [x] 3.5 Call sidecar `segment_audio` for VAD chunking
- [x] 3.6 For each chunk: call Dify STT API (`/v1/audio-to-text`)
- [x] 3.7 Implement retry with exponential backoff for Dify errors
- [x] 3.8 Concatenate chunk transcriptions
- [x] 3.9 Clean up temp files after processing
- [x] 3.10 Return final transcript with metadata
## 4. Frontend UI
- [x] 4.1 Add "Upload Audio" button in meeting-detail.html (next to recording controls)
- [x] 4.2 Implement file input with accepted audio formats
- [x] 4.3 Add upload progress indicator (upload phase)
- [x] 4.4 Add transcription progress indicator (chunk X of Y)
- [x] 4.5 Show confirmation dialog if transcript already has content
- [x] 4.6 Display transcription result in transcript area
- [x] 4.7 Handle error states (file too large, unsupported format, API error)
## 5. API Service
- [x] 5.1 Add `transcribeAudio()` function to `client/src/services/api.js`
- [x] 5.2 Implement FormData upload with progress tracking
- [x] 5.3 Handle streaming response for chunk progress
## 6. Testing
- [ ] 6.1 Test sidecar VAD segmentation with various audio lengths
- [ ] 6.2 Test with various audio formats (MP3, WAV, M4A, WebM, OGG)
- [ ] 6.3 Test with large file (>100MB) to verify chunking
- [ ] 6.4 Test error handling (invalid format, Dify timeout, API error)
- [ ] 6.5 Verify transcript displays correctly after upload
- [ ] 6.6 Test chunk concatenation quality (no missing content at boundaries)