Yera All
77df41bce0
fix(voice): race slow streaming asr finalize
2026-04-19 01:06:03 +05:00
Yera All
a44a1b97a1
feat(voice): start early replies before final asr
2026-04-19 00:46:16 +05:00
Yera All
9cd553bf92
feat(voice): start replies from stable streaming partials
2026-04-19 00:13:58 +05:00
Yera All
770ba4e925
feat(voice): add elevenlabs realtime streaming asr
2026-04-18 20:15:44 +05:00
Yera All
34b807e460
feat(voice): add elevenlabs stt and transcript truth fixes
2026-04-18 18:25:07 +05:00
Yera All
ac2269b6a4
fix(voice): correct yandex asr endpoints
2026-04-17 13:39:26 +05:00
Yera All
4adaf192fb
fix(voice): avoid silence on ASR runtime failures
2026-04-17 01:28:06 +05:00
Yera All
f66b289371
feat(voice): add Yandex streaming ASR
2026-04-17 01:06:45 +05:00
Yera All
5d40cfafd8
feat(voice): switch voice ASR to Yandex SpeechKit
2026-04-17 00:53:20 +05:00
Yera All
39096e114f
fix(voice): harden noisy streaming turns
2026-04-17 00:30:41 +05:00
Yera All
aa6f838061
fix(voice): keep asr partial polling off push path
2026-04-17 00:06:27 +05:00
Yera All
52b2edfcd3
fix(voice): stop thinking continuation on silence
2026-04-16 23:56:10 +05:00
Yera All
d331981ac8
fix(voice): decouple streaming asr from media loop
2026-04-16 23:11:24 +05:00
Yera All
5af47991dc
fix(voice): stabilize turn finalization after asr timeouts
2026-04-16 02:30:39 +05:00
Yera All
0d7e833a0d
fix(voice): ignore playback audio until real barge-in
2026-04-13 12:28:36 +05:00
Yera All and Claude Opus 4.6
6798320209
fix: remove dead code duplicates, add SQL LIMIT across all services
...
- Remove duplicate function definitions with hardcoded "AI-оператор" strings
(ai_voice_runtime, ai_orchestrator, voice_name_config, voice.py)
- Remove unreachable dead code after return in ai_voice_runtime
- Add SQL LIMIT to 17 unbounded queries across 12 services to prevent OOM
- Move Python-side filtering to SQL WHERE in reporting_service
- Downgrade 19 logger.warning to logger.info for normal-flow events in media_runtime
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-04-13 12:04:26 +05:00
Yera All
989bf9a0c1
fix(voice): stabilize v2 streaming topic handling
2026-04-12 21:59:32 +05:00
Yera All
57bd5cad4b
fix(voice): suppress low-signal turns and false lookup replies
2026-04-12 20:40:25 +05:00
Yera All
f2ece35588
fix(tests): isolate db state and stabilize voice runtime suite
2026-04-12 11:38:02 +05:00
Yera All
9386b8f9b9
feat(voice): add streaming asr sidecar for v2 duplex
2026-04-12 01:38:30 +05:00
Yera All
b75b76fae6
feat(voice): add duplex streaming v2 pipeline
2026-04-11 17:38:21 +05:00
Yera All
fc976804e4
feat(voice): add admin-configurable elevenlabs tts
2026-04-11 16:46:43 +05:00
Yera All
9d0b76deca
fix(voice): make fast ack more audible
2026-04-11 02:27:49 +05:00
Yera All
05dc31855d
feat(voice): add controlled emotive ack layer
2026-04-11 02:14:53 +05:00
Yera All
6413beeba1
feat(voice): emit immediate ack on turn close
2026-04-11 01:40:04 +05:00
Yera All
c39fad7e2d
feat(voice): add phase 1.1 partial asr fast ack
2026-04-11 01:24:21 +05:00
Yera All
5c1f720b46
feat(ai): apply 1.1x speed default to Yandex TTS as well
2026-04-07 00:45:09 +05:00
Yera All
025f1a59ce
chore(ai): lower VAD trailing silence to 500ms to reduce latency
2026-04-07 00:44:08 +05:00
Yera All
8ca773d27d
feat(ai): Add support for OpenAI TTS speed configuration, defaulting to 1.1x
2026-04-07 00:43:20 +05:00
Yera All
1497bb0feb
feat(ai): Finalize voice operator persona and voice name flow
2026-04-06 23:19:24 +05:00
Yera All
d959c2b2f0
Add voice name flow controls and analytics
2026-04-05 03:26:18 +05:00
Yera All
5374c202d9
Initial import with GitLab CI/CD and registry deploy flow
2026-04-02 17:05:45 +05:00
Yera All