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

Add should_interrupt + broadcast user events

Browse Source
This commit is contained in:
poseneror
2026-01-13 14:19:50 +02:00
parent b95a6afe77
commit 3304b18ac2
1 changed files with 13 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
src/pipecat/services/gladia/stt.py
View File

@@ -204,6 +204,7 @@ class GladiaSTTService(WebsocketSTTService):
model: str = "solaria-1", model: str = "solaria-1",
params: Optional[GladiaInputParams] = None, params: Optional[GladiaInputParams] = None,
max_buffer_size: int = 1024 * 1024 * 20, # 20MB default buffer max_buffer_size: int = 1024 * 1024 * 20, # 20MB default buffer
should_interrupt: bool = True,
**kwargs, **kwargs,
): ):
"""Initialize the Gladia STT service. """Initialize the Gladia STT service.
@@ -222,6 +223,8 @@ class GladiaSTTService(WebsocketSTTService):
model: Model to use for transcription. Defaults to "solaria-1". model: Model to use for transcription. Defaults to "solaria-1".
params: Additional configuration parameters for Gladia service. params: Additional configuration parameters for Gladia service.
max_buffer_size: Maximum size of audio buffer in bytes. Defaults to 20MB. max_buffer_size: Maximum size of audio buffer in bytes. Defaults to 20MB.
should_interrupt: Determine whether the bot should be interrupted when
Gladia VAD detects user speech. Defaults to True.
**kwargs: Additional arguments passed to the STTService parent class. **kwargs: Additional arguments passed to the STTService parent class.
""" """
super().__init__(sample_rate=sample_rate, **kwargs) super().__init__(sample_rate=sample_rate, **kwargs)
@@ -270,6 +273,7 @@ class GladiaSTTService(WebsocketSTTService):
# VAD state tracking # VAD state tracking
self._is_speaking = False self._is_speaking = False
self._should_interrupt = should_interrupt
def __str__(self): def __str__(self):
return f"{self.name} [{self._session_id}]" return f"{self.name} [{self._session_id}]"
@@ -515,25 +519,28 @@ class GladiaSTTService(WebsocketSTTService):
async def _on_speech_started(self): async def _on_speech_started(self):
"""Handle speech start event from Gladia. """Handle speech start event from Gladia.
Triggers interruption and emits UserStartedSpeakingFrame when VAD is enabled. Broadcasts UserStartedSpeakingFrame and optionally triggers interruption
when VAD is enabled.
""" """
if not self._params.enable_vad or self._is_speaking: if not self._params.enable_vad or self._is_speaking:
return return
logger.debug(f"{self} User started speaking") logger.debug(f"{self} User started speaking")
self._is_speaking = True self._is_speaking = True
# Push interruption first to stop the bot, then notify about user speaking
await self.push_interruption_task_frame_and_wait() await self.broadcast_frame(UserStartedSpeakingFrame)
await self.push_frame(UserStartedSpeakingFrame()) if self._should_interrupt:
await self.push_interruption_task_frame_and_wait()
async def _on_speech_ended(self): async def _on_speech_ended(self):
"""Handle speech end event from Gladia. """Handle speech end event from Gladia.
Emits UserStoppedSpeakingFrame when VAD is enabled. Broadcasts UserStoppedSpeakingFrame when VAD is enabled.
""" """
if not self._params.enable_vad or not self._is_speaking: if not self._params.enable_vad or not self._is_speaking:
return return
self._is_speaking = False self._is_speaking = False
await self.push_frame(UserStoppedSpeakingFrame()) await self.broadcast_frame(UserStoppedSpeakingFrame)
logger.debug(f"{self} User stopped speaking") logger.debug(f"{self} User stopped speaking")
async def _send_audio(self, audio: bytes): async def _send_audio(self, audio: bytes):