Skip to content

allow pushing frames to VAD when agent speech is uninterruptible #4418

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
chenghao-mou merged 2 commits into from
Jan 2, 2026
+10 −9
Merged

allow pushing frames to VAD when agent speech is uninterruptible #4418

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c611c42
allow pushing frames to VAD only
chenghao-mou Dec 30, 2025
91cac9a
fix type issues
chenghao-mou Dec 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions livekit-agents/livekit/agents/voice/agent_activity.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -735,19 +735,20 @@ def push_audio(self, frame: rtc.AudioFrame) -> None:
if not self._started:
return

if (
should_discard = bool(
self._current_speech
and not self._current_speech.allow_interruptions
and self._session.options.discard_audio_if_uninterruptible
):
# discard the audio if the current speech is not interruptable
return
)

if self._rt_session is not None:
self._rt_session.push_audio(frame)
if not should_discard:
if self._rt_session is not None:
self._rt_session.push_audio(frame)

# Always forward to _audio_recognition for VAD, even when discarding STT/LLM
# VAD needs frames to detect speech end and update user state correctly
if self._audio_recognition is not None:
self._audio_recognition.push_audio(frame)
self._audio_recognition.push_audio(frame, skip_stt=should_discard)

def push_video(self, frame: rtc.VideoFrame) -> None:
if not self._started:
Expand Down
4 changes: 2 additions & 2 deletions livekit-agents/livekit/agents/voice/audio_recognition.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,9 +180,9 @@ def stop(self) -> None:
self.update_stt(None)
self.update_vad(None)

def push_audio(self, frame: rtc.AudioFrame) -> None:
def push_audio(self, frame: rtc.AudioFrame, *, skip_stt: bool = False) -> None:
self._sample_rate = frame.sample_rate
if self._stt_ch is not None:
if not skip_stt and self._stt_ch is not None:
self._stt_ch.send_nowait(frame)

if self._vad_ch is not None:
Expand Down