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

Merge pull request #4344 from pipecat-ai/mb/11labs-normalized-alignment

Browse Source
This commit is contained in:
Mark Backman
2026-04-21 13:41:04 -04:00
committed by GitHub
parent b0e3b69b35 a07bee2318
commit 8e247f395b
2 changed files with 62 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4344.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` emitting word timestamps and `TTSTextFrame` content that matched the input text instead of the spoken audio when a pronunciation dictionary (`pronunciation_dictionary_locators`) or text normalization rewrote the input. Both services now consume ElevenLabs' normalized alignment, so downstream consumers (captions, transcripts, context aggregation) reflect what the listener actually hears.