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

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

Browse Source 
Do a consistency pass on how we're sending `UserStartedSpeakingFrame`…
This commit is contained in:
kompfner
2026-01-15 09:24:14 -05:00
committed by GitHub
parent dcd5840341 e107902b14
commit 24082b84f2
8 changed files with 9 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/foundational/22b-natural-conversation-proposal.py
View File

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

2
examples/foundational/22c-natural-conversation-mixed-llms.py
View File

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

2
examples/foundational/22d-natural-conversation-gemini-audio.py
View File

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

4
src/pipecat/services/aws/nova_sonic/llm.py
View File

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

3
src/pipecat/services/deepgram/flux/stt.py
View File

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

2
src/pipecat/services/grok/realtime/llm.py
View File

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

2
src/pipecat/services/openai/realtime/llm.py
View File

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

2
src/pipecat/services/openai_realtime_beta/openai.py
View File

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