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

tts: use smaller audio chunk sizes

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-04-16 11:35:36 -07:00
parent d05b2d0e8d
commit 6cea71270e
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/pipecat/services/aws/tts.py
View File

@@ -231,9 +231,9 @@ class PollyTTSService(TTSService):
yield TTSStartedFrame() yield TTSStartedFrame()
chunk_size = 8192 CHUNK_SIZE = 1024
for i in range(0, len(audio_data), chunk_size): for i in range(0, len(audio_data), CHUNK_SIZE):
chunk = audio_data[i : i + chunk_size] chunk = audio_data[i : i + CHUNK_SIZE]
if len(chunk) > 0: if len(chunk) > 0:
await self.stop_ttfb_metrics() await self.stop_ttfb_metrics()
frame = TTSAudioRawFrame(chunk, self.sample_rate, 1) frame = TTSAudioRawFrame(chunk, self.sample_rate, 1)

2
src/pipecat/services/elevenlabs/tts.py
View File

@@ -550,7 +550,7 @@ class ElevenLabsHttpTTSService(TTSService):
if self._settings["optimize_streaming_latency"] is not None: if self._settings["optimize_streaming_latency"] is not None:
params["optimize_streaming_latency"] = self._settings["optimize_streaming_latency"] params["optimize_streaming_latency"] = self._settings["optimize_streaming_latency"]
logger.debug(f"ElevenLabs request - payload: {payload}, params: {params}") logger.debug(f"{self} ElevenLabs request - payload: {payload}, params: {params}")
try: try:
await self.start_ttfb_metrics() await self.start_ttfb_metrics()

6
src/pipecat/services/google/tts.py
View File

@@ -346,9 +346,9 @@ class GoogleTTSService(TTSService):
audio_content = response.audio_content[44:] audio_content = response.audio_content[44:]
# Read and yield audio data in chunks # Read and yield audio data in chunks
chunk_size = 8192 CHUNK_SIZE = 1024
for i in range(0, len(audio_content), chunk_size): for i in range(0, len(audio_content), CHUNK_SIZE):
chunk = audio_content[i : i + chunk_size] chunk = audio_content[i : i + CHUNK_SIZE]
if not chunk: if not chunk:
break break
await self.stop_ttfb_metrics() await self.stop_ttfb_metrics()