Merge pull request #3453 from pipecat-ai/pk/consistency-pass-on-user-started-stopped-speaking-frames

Do a consistency pass on how we're sending `UserStartedSpeakingFrame`…

examples/foundational/22b-natural-conversation-proposal.py

@@ -119,7 +119,7 @@ class CompletenessCheck(FrameProcessor):
 
         if isinstance(frame, TextFrame) and frame.text == "YES":
             logger.debug("Completeness check YES")
-            await self.push_frame(UserStoppedSpeakingFrame())
+            await self.broadcast_frame(UserStoppedSpeakingFrame)
             await self._notifier.notify()
         elif isinstance(frame, TextFrame) and frame.text == "NO":
             logger.debug("Completeness check NO")

examples/foundational/22c-natural-conversation-mixed-llms.py

@@ -322,7 +322,7 @@ class CompletenessCheck(FrameProcessor):
 
         if isinstance(frame, TextFrame) and frame.text == "YES":
             logger.debug("!!! Completeness check YES")
-            await self.push_frame(UserStoppedSpeakingFrame())
+            await self.broadcast_frame(UserStoppedSpeakingFrame)
             await self._notifier.notify()
         elif isinstance(frame, TextFrame) and frame.text == "NO":
             logger.debug("!!! Completeness check NO")

examples/foundational/22d-natural-conversation-gemini-audio.py

@@ -451,7 +451,7 @@ class CompletenessCheck(FrameProcessor):
             logger.debug("Completeness check YES")
             if self._idle_task:
                 await self.cancel_task(self._idle_task)
-            await self.push_frame(UserStoppedSpeakingFrame())
+            await self.broadcast_frame(UserStoppedSpeakingFrame)
             await self._audio_accumulator.reset()
             await self._notifier.notify()
         elif isinstance(frame, TextFrame):

src/pipecat/services/aws/nova_sonic/llm.py

@@ -1187,7 +1187,7 @@ class AWSNovaSonicLLMService(LLMService):
             logger.debug(
                 "Wrapping assistant response trigger transcription with upstream UserStarted/StoppedSpeakingFrames"
             )
-            await self.push_frame(UserStartedSpeakingFrame(), direction=FrameDirection.UPSTREAM)
+            await self.broadcast_frame(UserStartedSpeakingFrame)
 
         # Send the transcription upstream for the user context aggregator
         frame = TranscriptionFrame(
@@ -1197,7 +1197,7 @@ class AWSNovaSonicLLMService(LLMService):
 
         # Finish wrapping the upstream transcription in UserStarted/StoppedSpeakingFrames if needed
         if should_wrap_in_user_started_stopped_speaking_frames:
-            await self.push_frame(UserStoppedSpeakingFrame(), direction=FrameDirection.UPSTREAM)
+            await self.broadcast_frame(UserStoppedSpeakingFrame)
 
         # Clear out the buffered user text
         self._user_text_buffer = ""

src/pipecat/services/deepgram/flux/stt.py

@@ -676,8 +676,7 @@ class DeepgramFluxSTTService(WebsocketSTTService):
 
         await self._handle_transcription(transcript, True, self._language)
         await self.stop_processing_metrics()
-        await self.push_frame(UserStoppedSpeakingFrame(), FrameDirection.DOWNSTREAM)
-        await self.push_frame(UserStoppedSpeakingFrame(), FrameDirection.UPSTREAM)
+        await self.broadcast_frame(UserStoppedSpeakingFrame)
         await self._call_event_handler("on_end_of_turn", transcript)
 
     async def _handle_eager_end_of_turn(self, transcript: str, data: Dict[str, Any]):

src/pipecat/services/grok/realtime/llm.py

@@ -659,7 +659,7 @@ class GrokRealtimeLLMService(LLMService):
         """Handle speech stopped event from VAD."""
         await self.start_ttfb_metrics()
         await self.start_processing_metrics()
-        await self.push_frame(UserStoppedSpeakingFrame())
+        await self.broadcast_frame(UserStoppedSpeakingFrame)
 
     async def _handle_evt_error(self, evt):
         """Handle error event."""

src/pipecat/services/openai/realtime/llm.py

@@ -776,7 +776,7 @@ class OpenAIRealtimeLLMService(LLMService):
     async def _handle_evt_speech_stopped(self, evt):
         await self.start_ttfb_metrics()
         await self.start_processing_metrics()
-        await self.push_frame(UserStoppedSpeakingFrame())
+        await self.broadcast_frame(UserStoppedSpeakingFrame)
 
     async def _maybe_handle_evt_retrieve_conversation_item_error(self, evt: events.ErrorEvent):
         """Maybe handle an error event related to retrieving a conversation item.

src/pipecat/services/openai_realtime_beta/openai.py

@@ -662,7 +662,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
     async def _handle_evt_speech_stopped(self, evt):
         await self.start_ttfb_metrics()
         await self.start_processing_metrics()
-        await self.push_frame(UserStoppedSpeakingFrame())
+        await self.broadcast_frame(UserStoppedSpeakingFrame)
 
     async def _maybe_handle_evt_retrieve_conversation_item_error(self, evt: events.ErrorEvent):
         """Maybe handle an error event related to retrieving a conversation item.