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

Changelog entries for the TTS improvements and fixes.

Browse Source
This commit is contained in:
filipi87
2026-03-06 16:16:25 -03:00
parent 07abd3d60f
commit 3000037dec
4 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3804.added.md Normal file
View File

@@ -0,0 +1 @@
- Added concurrent audio context support: `CartesiaTTSService` can now synthesize the next sentence while the previous one is still playing, by setting `pause_frame_processing=False` and routing each sentence through its own audio context queue.

1
changelog/3804.changed.md Normal file
View File

@@ -0,0 +1 @@
- Audio context management (previously in `AudioContextTTSService`) is now built into `TTSService`. All WebSocket providers (`cartesia`, `elevenlabs`, `asyncai`, `inworld`, `rime`, `gradium`, `resembleai`) now inherit from `WebsocketTTSService` directly. Word-timestamp baseline is set automatically on the first audio chunk of each context instead of requiring each provider to call `start_word_timestamps()` in their receive loop.

2
changelog/3804.deprecated.md Normal file
View File

@@ -0,0 +1,2 @@
- Deprecated `AudioContextTTSService` and `AudioContextWordTTSService`. Subclass `WebsocketTTSService` directly instead; audio context management is now part of the base `TTSService`.
- Deprecated `WordTTSService`, `WebsocketWordTTSService`, and `InterruptibleWordTTSService`. Word timestamp logic is now always active in `TTSService` and no longer needs to be opted into via a subclass.

1
changelog/3804.removed.md Normal file
View File

@@ -0,0 +1 @@
- ⚠️ Removed `supports_word_timestamps` parameter from `TTSService.__init__()`. Word timestamp logic is now always active. Remove this argument from any custom subclass `super().__init__()` calls.