hailin ba83e433d3 feat: enable OpenAI Realtime STT for streaming speech recognition ... Switch from batch STT (gpt-4o-transcribe via /audio/transcriptions) to streaming Realtime API (WebSocket). This eliminates the ~2s batch upload+process latency per utterance. Also updated nginx proxy on 67.223.119.33 to support WebSocket upgrade for /v1/realtime endpoint. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-01 07:49:25 -08:00
..
src	feat: enable OpenAI Realtime STT for streaming speech recognition	2026-03-01 07:49:25 -08:00
Dockerfile	fix: resolve websockets version conflict and use CPU-only torch	2026-02-28 09:02:31 -08:00
requirements.txt	fix: resolve websockets version conflict and use CPU-only torch	2026-02-28 09:02:31 -08:00