restore: Bring back full VoiceCal WebRTC interface
Peter Michael Gits+1: Claude
3763b20
- Restore streamlit_websocket_app.py from backup with full WebRTC functionality
- Update README.md app_file to point to main application
- Add necessary requirements for WebRTC integration
- Keep .streamlit/config.toml for proper HF Spaces configuration
- Now that infrastructure works, restore complete voice interface
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
debug: Switch to ultra-minimal Streamlit test to isolate restart loop issue
Peter Michael Gits+1: Claude
4a0bb42
- Create minimal_test.py with only basic Streamlit components
- Change app_file to minimal_test.py in README.md for HF Spaces
- Remove st.set_page_config() from main app temporarily
- Test if complex Streamlit components are causing restart loops
- Will identify root cause before re-adding functionality
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
debug: Simplify VoiceCal to isolate restart issue cause
Peter Michael Gits+1: Claude
ae83ce7
- Remove complex JavaScript WebRTC integration temporarily
- Create minimal Streamlit interface for startup debugging
- Backup original version as streamlit_websocket_app.py.backup
- Add test_streamlit_simple.py for isolated testing
- Focus on basic Streamlit functionality first
- Will re-add WebRTC after confirming basic startup works
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
refactor: Streamline VoiceCal to pure WebSocket connectivity with STT v1.0.0
Peter Michael Gits+1: Claude
1c5ac0f
- Updated WebSocket URL to /ws/stt for standalone STT service
- Added sendAudioViaWebSocket() method with base64 audio transmission
- Commented out HTTP API fallback code (focusing on WebSocket-only)
- Enhanced STT response handling for standalone service v1.0.0
- Updated WebSocket test connection method
- Modified UI to reflect "Pure WebSocket" and "No fallbacks" approach
- Technical documentation updated for standalone STT integration
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
fix: Switch to Gradio HTTP API fallback for WebSocket connectivity issues
Peter Michael Gits+1: Claude
8527d70
- Use /api/predict endpoint instead of WebSocket due to Gradio routing conflicts
- Maintain WebRTC audio capture with WebM/Opus format
- Add fallback mechanism for reliable STT integration
- Compatible with new standalone WebSocket STT service v1.0.0
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
fix: Update WebSocket URL to /api/ws/stt to avoid Gradio routing conflicts
Peter Michael Gits+1: Claude
a312290
- Change STT WebSocket path from /ws/stt to /api/ws/stt
- This path should avoid conflicts with Gradio's internal routing
- Update VoiceCal client to use new WebSocket endpoint
- Add logging to show alternative path being used
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
fix: Simplify VoiceCal to single Streamlit service with direct STT connection
Peter Michael Gits+1: Claude
e118f9c
- Replace complex nginx reverse proxy setup with simple Streamlit app
- Create streamlit_websocket_app.py with direct STT WebSocket connection
- Eliminate multi-service complexity that was causing HF Spaces deployment issues
- Implement direct connection to wss://pgits-stt-gpu-service.hf.space/ws/stt
- Maintain unmute.sh pattern with simplified architecture:
* WebRTC MediaRecorder for audio capture
* Direct WebSocket communication to STT service
* Real-time transcription display
- Much better compatibility with HuggingFace Spaces constraints
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
