Commit Graph
34 Commits
Author SHA1 Message Date
didar 26d718b0ae feat: enable streaming TTS for improved voice interaction
deploy / deploy (push) Successful in 30s
2026-08-29 00:29:44 +05:00
didar d9437d8b21 feat: update ElevenLabs API keys and voice IDs for improved ASR and TTS functionality
deploy / deploy (push) Successful in 32s
2026-08-28 23:45:34 +05:00
didar b474c35608 feat: enhance acknowledgment responses for Kazakh and Russian languages
deploy / deploy (push) Successful in 33s
2026-08-28 15:12:19 +05:00
didarandClaude Sonnet 5 fadff59512 feat: reduce VAD trailing silence for faster voice bot response
deploy / deploy (push) Successful in 30s
Lower AI_VOICE_VAD_TRAILING_SILENCE_MS from 500 to 350 so the bot
starts responding sooner after the caller stops speaking.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-25 16:59:00 +05:00
didarandClaude Sonnet 5 7f03b26ef6 feat: switch ElevenLabs RU/KK voice to softer, younger female voice
deploy / deploy (push) Successful in 2m50s
Swap RU and KK TTS voice IDs to "Nataly Mi Soft voice" — a soft,
gentle, young female voice verified for Russian on eleven_turbo_v2_5.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-25 16:23:44 +05:00
didar 953268e1b8 feat: update ElevenLabs RU voice ID for improved TTS performance
deploy / deploy (push) Successful in 31s
2026-08-25 02:09:48 +05:00
didar f9793dc5f4 feat: enable emotive acknowledgments and update ElevenLabs TTS model ID for enhanced audio responses
deploy / deploy (push) Successful in 30s
2026-08-25 02:00:26 +05:00
didar 7ddc965292 fix: disable AI_VOICE_V2_STREAMING_TTS for improved stability
deploy / deploy (push) Successful in 30s
2026-08-25 01:50:31 +05:00
didar 2ea6e6f4bb feat: update AI voice settings for improved responsiveness and pacing
deploy / deploy (push) Successful in 31s
2026-08-25 01:42:10 +05:00
didar 6ccdaf9167 feat: update ElevenLabs TTS model ID and add prebuffering for improved audio streaming
deploy / deploy (push) Successful in 31s
2026-08-25 01:20:52 +05:00
didar 70ec9ab384 feat: retrieving back ElevenLabs TTS model ID to eleven_flash_v2_5
deploy / deploy (push) Successful in 30s
2026-08-25 01:09:26 +05:00
didar c399296165 feat: implement no-speech reprompt functionality with configurable parameters
deploy / deploy (push) Successful in 33s
2026-08-24 14:17:00 +05:00
didarandClaude Sonnet 5 75d9ed85a7 fix: force narrowband slin on AI audiosocket channel
deploy / deploy (push) Successful in 31s
AudioSocket was delivering 16kHz audio despite the telecom-kz trunk being
codec-restricted to alaw/ulaw, causing the 8k->16k ASR resample to double
an already-16kHz stream to an effective 32kHz labeled as 16000 Hz -
audible as slow, deep-pitched, unintelligible speech. Force
audioread/writeformat=slin before AudioSocket() so the channel always
delivers narrowband 8kHz, matching every rate assumption in the runtime.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-23 15:42:01 +05:00
didar c590528694 feat: add debug audio dump functionality for ElevenLabs ASR provider
deploy / deploy (push) Successful in 30s
2026-08-23 13:38:56 +05:00
didar 206b0bafe0 feat: update real-time commit strategy for ElevenLabs ASR to VAD
deploy / deploy (push) Successful in 30s
2026-08-23 13:05:58 +05:00
Codex 6d9b0ce98a feat: add aimaq production env file (TTS/ASR/LLM config in git)
deploy / deploy (push) Successful in 29s
2026-08-21 13:37:25 +00:00
didar ffa779ffa0 Move ai-voice-runtime-service host port off 9019 to avoid cross-tenant conflict
deploy / deploy (push) Canceled after 24h48m11s
A separate deployment on the same host (aimaq-call-center) already binds
127.0.0.1:9019, so this project's ai-voice-runtime-service could never
start there. Remap the host side to 9024 and point Asterisk's
AudioSocket target at the new port; the container still listens on 9019
internally.
2026-08-20 23:22:16 +05:00
arys f53af1f7dc sales fix 2026-05-09 09:16:06 +05:00
Yera All 770ba4e925 feat(voice): add elevenlabs realtime streaming asr 2026-04-18 20:15:44 +05:00
Yera All 25480fc903 fix(deploy): allow voice provider env overrides 2026-04-18 18:43:36 +05:00
Yera All feb0ce01e2 fix(asterisk): update telecom route and recording fallback 2026-04-17 12:16:51 +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 213057efeb Revert "feat(asterisk): add telecom.kz IP trunk for DID 87273901485"
This reverts commit 436821737e.
2026-04-16 01:27:34 +05:00
Yera AllandClaude Opus 4.6 436821737e feat(asterisk): add telecom.kz IP trunk for DID 87273901485
Wires the production number 87273901485 (SIP account 86205414@sip.telecom.kz)
into the voice stack as a no-registration IP trunk. Inbound INVITEs are
identified by source IP 92.46.61.21 and routed straight into the AI-first
entrypoint (7100), with the existing AudioSocket -> live operator fallback
preserved.

The Asterisk container was also never started by the source-based CI deploy
(only the registry-based path brought it up). Patch scripts/deploy_gitlab.sh
to also run docker-compose.asterisk.server.yml so the voice channel stays in
sync with the rest of the platform on every push to the default branch.

- deployment/asterisk/pjsip.conf: add telecom-kz aor/auth/endpoint/identify
- deployment/asterisk/entrypoint.sh: inject ASTERISK_TELECOM_KZ_PASSWORD
- deployment/asterisk/extensions.conf: new [from-telecom] context -> 7100
- .env.production.template: document ASTERISK_TELECOM_KZ_PASSWORD
- scripts/deploy_gitlab.sh: also bring up the asterisk compose file

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-16 01:19:06 +05:00
Yera All 6b8f5d069b feat(ai): add rolling conversation summary memory 2026-04-13 11:59:43 +05:00
Yera All a5b402f329 fix(deploy): pass sidecar app module at container runtime 2026-04-12 14:26:24 +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 05dc31855d feat(voice): add controlled emotive ack layer 2026-04-11 02:14:53 +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 1ff8fd7102 docs: recreate documentation structure with updated specs 2026-04-06 23:19:24 +05:00
Your Name 6cebd8216c Automate source deployment on main 2026-04-04 03:10:08 +05:00
Yera All 5374c202d9 Initial import with GitLab CI/CD and registry deploy flow 2026-04-02 17:05:45 +05:00