Merge pull request #1681 from pipecat-ai/aleix/tts-service-llm-full-response-end-fix

TTSService: do not push LLMFullResponseEndFrame if not needed
2025-04-28 12:00:55 -07:00
parent 3d05a74dc0 e3c965f4d5
commit 8accd3e387
5 changed files with 18 additions and 11 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -73,6 +73,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ### Fixed

+- Fixed a TTS services issue that could cause assistant output not to be
+  aggregated to the context when also using `TTSSpeakFrame`s.
+
 - Fixed an issue where the `SmartTurnMetricsData` was reporting 0ms for
  inference and processing time when using the `FalSmartTurnAnalyzer`.