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

introduce PipelineParams audio input/output sample rates

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-02-04 12:22:41 -08:00
parent cc54255c41
commit ab45e481be
61 changed files with 570 additions and 402 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/foundational/07g-interruptible-openai-tts.py
View File

@@ -37,7 +37,6 @@ async def main():
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=24000,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),

1
examples/foundational/07k-interruptible-lmnt.py
View File

@@ -38,7 +38,6 @@ async def main():
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=24000,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),

1
examples/foundational/07n-interruptible-google.py
View File

@@ -40,7 +40,6 @@ async def main():
"Respond bot",
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=24000,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,

7
examples/foundational/09-mirror.py
View File

@@ -21,7 +21,7 @@ from pipecat.frames.frames import (
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -61,7 +61,6 @@ async def main():
"Test",
DailyParams(
audio_in_enabled=True,
audio_in_sample_rate=24000,
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_is_live=True,
@@ -78,7 +77,9 @@ async def main():
runner = PipelineRunner()
task = PipelineTask(pipeline)
task = PipelineTask(
pipeline, PipelineParams(audio_in_sample_rate=24000, audio_out_sample_rate=24000)
)
await runner.run(task)

8
examples/foundational/09a-local-mirror.py
View File

@@ -22,7 +22,7 @@ from pipecat.frames.frames import (
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.local.tk import TkLocalTransport
@@ -62,7 +62,7 @@ async def main():
tk_root.title("Local Mirror")
daily_transport = DailyTransport(
room_url, token, "Test", DailyParams(audio_in_enabled=True, audio_in_sample_rate=24000)
room_url, token, "Test", DailyParams(audio_in_enabled=True)
)
tk_transport = TkLocalTransport(
@@ -82,7 +82,9 @@ async def main():
pipeline = Pipeline([daily_transport.input(), MirrorProcessor(), tk_transport.output()])
task = PipelineTask(pipeline)
task = PipelineTask(
pipeline, PipelineParams(audio_in_sample_rate=24000, audio_out_sample_rate=24000)
)
async def run_tk():
while not task.has_finished():

2
examples/foundational/18-gstreamer-filesrc.py
View File

@@ -51,8 +51,6 @@ async def main():
out_params=GStreamerPipelineSource.OutputParams(
video_width=1280,
video_height=720,
audio_sample_rate=24000,
audio_channels=1,
),
)

2
examples/foundational/19-openai-realtime-beta.py
View File

@@ -80,9 +80,7 @@ async def main():
"Respond bot",
DailyParams(
audio_in_enabled=True,
audio_in_sample_rate=24000,
audio_out_enabled=True,
audio_out_sample_rate=24000,
transcription_enabled=False,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),

2
examples/foundational/20b-persistent-context-openai-realtime.py
View File

@@ -177,9 +177,7 @@ async def main():
"Respond bot",
DailyParams(
audio_in_enabled=True,
audio_in_sample_rate=24000,
audio_out_enabled=True,
audio_out_sample_rate=24000,
transcription_enabled=False,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),

4
examples/foundational/21-tavus-layer.py
View File

@@ -88,6 +88,10 @@ async def main():
task = PipelineTask(
pipeline,
PipelineParams(
# We just use 16000 because that's what Tavus is expecting and
# we avoid resampling.
audio_in_sample_rate=16000,
audio_out_sample_rate=16000,
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,

1
examples/foundational/22d-natural-conversation-gemini-audio.py
View File

@@ -639,7 +639,6 @@ async def main():
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,
audio_in_sample_rate=16000,
),
)

2
examples/foundational/26-gemini-multimodal-live.py
View File

@@ -37,8 +37,6 @@ async def main():
token,
"Respond bot",
DailyParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,

2
examples/foundational/26a-gemini-multimodal-live-transcription.py
View File

@@ -37,8 +37,6 @@ async def main():
token,
"Respond bot",
DailyParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,

2
examples/foundational/26b-gemini-multimodal-live-function-calling.py
View File

@@ -84,8 +84,6 @@ async def main():
token,
"Respond bot",
DailyParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,

4
examples/foundational/26c-gemini-multimodal-live-video.py
View File

@@ -37,8 +37,6 @@ async def main():
token,
"Respond bot",
DailyParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,
@@ -47,8 +45,6 @@ async def main():
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
start_audio_paused=True,
start_video_paused=True,
),
)

2
examples/foundational/26d-gemini-multimodal-live-text.py
View File

@@ -52,8 +52,6 @@ async def main():
token,
"Respond bot",
DailyParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,

7
examples/foundational/29-livekit-audio-chat.py
View File

@@ -38,8 +38,6 @@ load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
DESIRED_SAMPLE_RATE = 16000
def generate_token(room_name: str, participant_name: str, api_key: str, api_secret: str) -> str:
token = api.AccessToken(api_key, api_secret)
@@ -114,11 +112,8 @@ async def main():
token=token,
room_name=room_name,
params=LiveKitParams(
audio_in_channels=1,
audio_in_enabled=True,
audio_out_enabled=True,
audio_in_sample_rate=DESIRED_SAMPLE_RATE,
audio_out_sample_rate=DESIRED_SAMPLE_RATE,
vad_analyzer=SileroVADAnalyzer(),
vad_enabled=True,
vad_audio_passthrough=True,
@@ -128,7 +123,6 @@ async def main():
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
live_options=LiveOptions(
sample_rate=DESIRED_SAMPLE_RATE,
vad_events=True,
),
)
@@ -138,7 +132,6 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
sample_rate=DESIRED_SAMPLE_RATE,
)
messages = [