wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #3958 from pipecat-ai/mb/deepgram-tts-audio-context

Browse Source 
Route Deepgram WebSocket TTS audio through audio context queue
This commit is contained in:
Mark Backman
2026-03-10 11:37:39 -04:00
committed by GitHub
parent c660152a84 50cc01a578
commit 2ce9179662
4 changed files with 24 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3958.changed.md Normal file
View File

@@ -0,0 +1 @@
- Changed `DeepgramTTSService` to send a Clear message on interruption instead of disconnecting and reconnecting the WebSocket, allowing the connection to persist throughout the session.

1
changelog/3958.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed `TTSService` audio context queue getting blocked when `append_to_audio_context()` was called with a `None` context ID, which prevented subsequent audio from being delivered.