services(TTSService): fix sentence cleanup

CHANGELOG.md

@@ -24,6 +24,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `TTSService` end of sentence detection has been improved. It now works with
   acronyms, numbers, hours and others.
 
+- Fixed an issue in `TTSService` that would not properly flush the current
+  aggregated sentence if an `LLMFullResponseEndFrame` was found.
+
 ### Performance
 
 - `CartesiaTTSService` now uses websockets which improves speed. It also

src/pipecat/services/ai_services.py

@@ -201,8 +201,9 @@ class TTSService(AIService):
         elif isinstance(frame, StartInterruptionFrame):
             await self._handle_interruption(frame, direction)
         elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(frame, EndFrame):
+            sentence = self._current_sentence
             self._current_sentence = ""
-            await self._push_tts_frames(self._current_sentence)
+            await self._push_tts_frames(sentence)
             if isinstance(frame, LLMFullResponseEndFrame):
                 if self._push_text_frames:
                     await self.push_frame(frame, direction)