Skip to content

V2#37

Merged
sopaco merged 5 commits intomainfrom
v2
Feb 24, 2026
Merged

V2#37
sopaco merged 5 commits intomainfrom
v2

Conversation

@sopaco
Copy link
Copy Markdown
Owner

@sopaco sopaco commented Feb 24, 2026

No description provided.

Introduce comprehensive audio handling with three new modules:
- Audio capture using CPAL with gain and RAII cleanup
- Voice activity detection with configurable state machine
- Whisper-based transcription with Chinese optimization

These modules provide end-to-end audio processing from microphone
input to speech-to-text transcription, supporting multi-threaded
operation and proper resource management.
Integrate Whisper-based speech recognition with real-time audio capture
and voice activity detection. Users can now enable/disable microphone
input
via slash commands (/enable-audio-input, /disable-audio-input) to send
transcribed messages to the AI chat.
- Delete axum HTTP server implementation and related dependencies
- Remove API models, endpoint handlers, and routing logic
- Drop Voice Activity Detection (VAD) module
- Clean up module declarations for removed components
@sopaco sopaco merged commit f9c80d7 into main Feb 24, 2026
1 check failed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant