Fix: Cartesia's spelling feature adds whole word to context

This commit is contained in:
Mark Backman
2025-04-09 14:32:53 -04:00
parent 0df065fda4
commit 06be20eb16
2 changed files with 5 additions and 0 deletions

View File

@@ -66,6 +66,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Updated `daily-python` to 0.17.0 to fix an issue that was preventing to run on
older platforms.
- Fixed an issue where `CartesiaTTSService`'s spell feature would result in
the spelled word in the context appearing as "F,O,O,B,A,R" instead of
"FOOBAR".
- Fixed an issue in the Azure TTS services where the language was being set
incorrectly.

View File

@@ -166,6 +166,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
"output_format": self._settings["output_format"],
"language": self._settings["language"],
"add_timestamps": add_timestamps,
"use_original_timestamps": True,
}
return json.dumps(msg)