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

base_output: only generate bot speaking with TTS audio frames

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-10-31 15:40:35 -07:00
parent e2b1b56e86
commit d2401a76c8
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/pipecat/transports/base_output.py
View File

@@ -28,6 +28,7 @@ from pipecat.frames.frames import (
StartInterruptionFrame,
StopInterruptionFrame,
SystemFrame,
TTSAudioRawFrame,
TransportMessageFrame,
TransportMessageUrgentFrame,
)
@@ -397,13 +398,15 @@ class BaseOutputTransport(FrameProcessor):
frame = await asyncio.wait_for(self._audio_out_queue.get(), timeout=wait_time)
# Notify the bot started speaking upstream if necessary.
await self._bot_started_speaking()
if isinstance(frame, TTSAudioRawFrame):
await self._bot_started_speaking()
# Send audio.
await self.write_raw_audio_frames(frame.audio)
# Notify the bot is speaking upstream.
await self.push_frame(BotSpeakingFrame(), FrameDirection.UPSTREAM)
if isinstance(frame, TTSAudioRawFrame):
await self.push_frame(BotSpeakingFrame(), FrameDirection.UPSTREAM)
# Push frame downstream in case anyone else needs it.
await self.push_frame(frame)