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

BaseOutputTransport: optimize BotSpeakingFrames

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-04-01 10:07:44 -07:00
parent 3efbcab39c
commit bfd06b321d
2 changed files with 27 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/pipecat/transports/base_output.py
View File

@@ -336,13 +336,22 @@ class BaseOutputTransport(FrameProcessor):
return without_mixer(BOT_VAD_STOP_SECS)
async def _sink_task_handler(self):
# Push a BotSpeakingFrame every 200ms, we don't really need to push it
# at every audio chunk. If the audio chunk is bigger than 200ms, push at
# every audio chunk.
TOTAL_CHUNK_MS = self._params.audio_out_10ms_chunks * 10
BOT_SPEAKING_CHUNK_PERIOD = max(int(200 / TOTAL_CHUNK_MS), 1)
bot_speaking_counter = 0
async for frame in self._next_frame():
# Notify the bot started speaking upstream if necessary and that
# it's actually speaking.
if isinstance(frame, TTSAudioRawFrame):
await self._bot_started_speaking()
await self.push_frame(BotSpeakingFrame())
await self.push_frame(BotSpeakingFrame(), FrameDirection.UPSTREAM)
if bot_speaking_counter % BOT_SPEAKING_CHUNK_PERIOD == 0:
await self.push_frame(BotSpeakingFrame())
await self.push_frame(BotSpeakingFrame(), FrameDirection.UPSTREAM)
bot_speaking_counter = 0
bot_speaking_counter += 1
# No need to push EndFrame, it's pushed from process_frame().
if isinstance(frame, EndFrame):