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

Add audio flushing after sending text in RimeNonJsonTTSService

Browse Source 
This update ensures that audio is flushed immediately after sending bare text to the WebSocket, improving the responsiveness of the Text-to-Speech service.
This commit is contained in:
Gokul Js
2025-11-19 22:19:00 +05:30
parent afeef94900
commit 1d9696e614
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/pipecat/services/rime/tts.py
View File

@@ -833,6 +833,7 @@ class RimeNonJsonTTSService(InterruptibleTTSService):
# Send bare text (not JSON) # Send bare text (not JSON)
await self._get_websocket().send(text) await self._get_websocket().send(text)
await self.start_tts_usage_metrics(text) await self.start_tts_usage_metrics(text)
await self.flush_audio()
except Exception as e: except Exception as e:
logger.error(f"{self} exception: {e}") logger.error(f"{self} exception: {e}")