mateaix
|
197e697173
|
fix(stt): repair DashScope audio decoding (#580)
|
2026-08-10 21:43:02 +08:00 |
|
matevip
|
4c9394a86f
|
fix(stt): surface endpoint, status and body diagnostics on STT failures (#580)
|
2026-08-05 04:26:30 -04:00 |
|
mateaix
|
a578c8ef0e
|
fix(stt): replace DashScope realtime WS replay with synchronous Qwen3-ASR HTTP recognition (#580)
|
2026-08-04 21:53:25 +08:00 |
|
matevip
|
88fb28a22a
|
feat(stt): route OpenAI Whisper provider to any OpenAI-compatible endpoint (#76)
|
2026-05-09 13:57:52 +08:00 |
|
matevip
|
b7c911f01d
|
feat(stt): DashScope realtime voice + language-aware routing + TalkMode polish
- DashScope paraformer-realtime-v2 WebSocket streaming
- Language-aware provider routing: Whisper for English, Paraformer for Chinese
- PCM WAV recording replaces WebM (provider filename bug + diagnostics)
- TalkMode push-to-talk fixes (audio drop, WS connecting race)
- Vite dev proxy WebSocket upgrade fix
- WebSocket binary buffer 8KB → 8MB (Tomcat default truncated voice clips)
- Audio chunk pacing at 100ms (DashScope returned 0 chars otherwise)
- Resolved language hint propagation + raw frame logging
- V46 seed idempotency fix on UI-toggled STT row
- Diagnostic cleanup after debugging session
|
2026-04-26 16:37:55 +08:00 |
|
matevip
|
7007ea844d
|
feat: add TTS, STT, music generation, video providers (Runway/MiniMax), image providers (Google Imagen/MiniMax), and tool registry fix
|
2026-04-08 08:49:09 +08:00 |
|