hailin 186234bae2 fix: increase STT silence_duration_ms to prevent choppy transcription ... Default silence_duration_ms=350 is too aggressive for Chinese speech, causing sentences to be fragmented into 1-3 character chunks. Increase to 800ms and raise VAD threshold to 0.6 so the STT waits longer before finalizing a turn, producing complete sentences for LLM processing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-01 18:37:13 -08:00
..
plugins	fix: disable SSL verify for self-signed OpenAI proxy + handle no-user-msg	2026-02-28 21:39:49 -08:00
__init__.py	feat: migrate voice call from WebSocket/PCM to LiveKit WebRTC	2026-02-28 08:55:33 -08:00
agent.py	fix: increase STT silence_duration_ms to prevent choppy transcription	2026-03-01 18:37:13 -08:00
config.py	feat: upgrade TTS to gpt-4o-mini-tts with voice instructions	2026-03-01 08:19:05 -08:00