CRITICAL FIX: Return single value from gradio_transcribe_memory endpoint

feat: Add in-memory transcription path for true unmute.sh methodology

fix: Add ZeroGPU-specific environment variables for quota authentication

fix: Enhanced ZeroGPU authentication with multiple methods and debugging

fix: Move HuggingFace authentication before spaces import for proper ZeroGPU quota

trigger: Bump version to v1.0.1 to force rebuild with HF_TOKEN

feat: Add HuggingFace authentication to increase ZeroGPU quota

fix: Enable verbose error reporting in STT service Gradio interface

debug: Add comprehensive logging to verify STT service audio reception

fix: Simplify to Gradio-only interface to resolve port conflicts

feat: Add HTTP API transcription endpoint for Streamlit integration

fix: Replace demo.fastapi_app with proper FastAPI mounting for HF Spaces

fix: Integrate WebSocket endpoints into Gradio's internal FastAPI app

fix: Resolve STT service port conflict by removing manual demo.launch()

fix: Resolve STT service restart loop by removing conflicting Dockerfile

trigger: Force HuggingFace Spaces rebuild for latest hybrid implementation

feat: Implement hybrid Gradio+FastAPI WebSocket service for ZeroGPU compatibility

fix: Configure STT service for HuggingFace Spaces Docker deployment

fix: Resolve @spaces.GPU decorator NotImplementedError in STT service

feat: Replace STT service with standalone WebSocket-only architecture v1.0.0

feat: Add standalone WebSocket-only STT service v1.0.0

fix: Change WebSocket endpoint to /api/ws/stt to avoid Gradio conflicts

fix: Remove invalid router.setup() call causing AttributeError

fix: Use FastAPI router direct manipulation for WebSocket endpoint

fix: Improve WebSocket endpoint registration using add_api_websocket_route

fix: Resolve syntax error with WebSocket exception handling indentation

fix: Move WebSocket endpoint registration before Gradio launch

fix: Add working WebSocket endpoint integration for VoiceCal communication

fix: Remove hanging WebSocket post-launch integration

fix: Simplify WebSocket integration with post-launch mounting

fix: Resolve syntax error in exception handling

fix: Integrate WebSocket endpoints before Gradio starts

fix: Integrate WebSocket endpoints with Gradio on same port

fix: Enable STT_SERVICE_MODE environment variable reading

fix: Enable verbose error reporting in STT service

fix: Change default service mode to triple for ZeroGPU detection

feat: Add Whisper corruption detection and alternative STT models

feat: Add preload endpoints to STT service v0.6.2

feat: Implement unmute.sh methodology for STT service v0.6.0

fix: Improve WebM audio processing accuracy

fix: Add raw WebM processing fallback for HF Spaces

refactor: Implement unmute.sh-style direct audio processing

fix: Add WebM to WAV conversion using ffmpeg subprocess

fix: Add WebM audio format support for WebRTC compatibility

fix: Add dummy @spaces.GPU function to satisfy ZeroGPU startup requirements

fix: Display correct wss:// URLs for Hugging Face Spaces in STT service logs

temp: Force WebSocket mode while debugging environment variables

feat: Add clear environment variable logging to STT service

feat: Add WebSocket support for real-time STT integration

fix: Add MCP-compatible SafeStream with buffer attribute and stream restoration