hailin
186234bae2
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> |
||
|---|---|---|
| .. | ||
| agent-service | ||
| audit-service | ||
| auth-service | ||
| comm-service | ||
| inventory-service | ||
| monitor-service | ||
| ops-service | ||
| voice-agent | ||
| voice-service | ||