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

Improve docstring formatting in RimeNonJsonTTSService for better readability

Browse Source
This commit is contained in:
Gokul Js
2025-12-08 19:45:13 +05:30
parent 0707141998
commit e5fb643cf5
1 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/pipecat/services/rime/tts.py
View File

@@ -584,12 +584,18 @@ class RimeHttpTTSService(TTSService):
class RimeNonJsonTTSService(InterruptibleTTSService):
"""Pipecat TTS service for Rime's non-JSON WebSocket API.
This service enables Text-to-Speech synthesis over WebSocket endpoints that require plain text (not JSON) messages and return raw audio bytes. It is designed for use with TTS models like Arcana, which currently do not support JSON-based WebSocket protocols (though this may change in the future).
This service enables Text-to-Speech synthesis over WebSocket endpoints
that require plain text (not JSON) messages and return raw audio bytes.
It is designed for use with TTS models like Arcana, which currently do
not support JSON-based WebSocket protocols (though this may change in
the future).
Limitations:
- Does not support word-level timestamps or context IDs.
- Intended specifically for integrations where the TTS provider only accepts and returns non-JSON messages.
- Arcana and similar models may add JSON WebSocket support in the future; this service focuses on the current plain text protocol.
- Intended specifically for integrations where the TTS provider only
accepts and returns non-JSON messages.
- Arcana and similar models may add JSON WebSocket support in the
future; this service focuses on the current plain text protocol.
"""
class InputParams(BaseModel):