digiops/call-center
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: revert AI_VOICE_V2_STREAMING_TTS to disabled
deploy / deploy (push) Successful in 28s
Details

Browse Source 
Streaming TTS caused poor voice quality in live testing on Creator
plan too — not just a quota-era fluke. Reverting to non-streaming
synthesis until the root cause is understood.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
didar
2026-08-29 00:39:46 +05:00
co-authored by Claude Sonnet 5
parent 26d718b0ae
commit b8c922c9cf
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deployment/aimaq.env.production
+1 -1
View File
@@ -45,7 +45,7 @@ AI_VOICE_V2_PARTIAL_ASR=1
AI_VOICE_V2_PREBAKED_ACK_ENABLED=1
AI_VOICE_V2_EMOTIVE_ACK_ENABLED=1
AI_VOICE_V2_EMOTIVE_ACK_RU_ONLY=1
AI_VOICE_V2_STREAMING_TTS=1
AI_VOICE_V2_STREAMING_TTS=0
AI_VOICE_V2_STREAMING_ASR_BACKEND=elevenlabs_realtime
AI_VOICE_V2_STREAMING_ASR_BASE_URL=http://streaming-asr-sidecar:8021
AI_VOICE_V2_STREAMING_ASR_TIMEOUT_SECONDS=15