95 lines
2.8 KiB
Python
95 lines
2.8 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
import os
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||
from pipecat.pipeline.pipeline import Pipeline
|
||
from pipecat.pipeline.runner import PipelineRunner
|
||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.ultravox.stt import UltravoxSTTService
|
||
from pipecat.transports.base_transport import TransportParams
|
||
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
|
||
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
|
||
|
||
load_dotenv(override=True)
|
||
|
||
# NOTE: This example requires GPU resources to run efficiently.
|
||
# The Ultravox model is compute-intensive and performs best with GPU acceleration.
|
||
# This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
|
||
|
||
|
||
# Want to initialize the ultravox processor since it takes time to load the model and dont
|
||
# want to load it every time the pipeline is run
|
||
ultravox_processor = UltravoxSTTService(
|
||
model_name="fixie-ai/ultravox-v0_5-llama-3_1-8b",
|
||
hf_token=os.getenv("HF_TOKEN"),
|
||
)
|
||
|
||
|
||
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
|
||
logger.info(f"Starting bot")
|
||
|
||
transport = SmallWebRTCTransport(
|
||
webrtc_connection=webrtc_connection,
|
||
params=TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
),
|
||
)
|
||
|
||
tts = CartesiaTTSService(
|
||
api_key=os.environ.get("CARTESIA_API_KEY"),
|
||
voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
|
||
)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
ultravox_processor,
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
allow_interruptions=True,
|
||
enable_metrics=True,
|
||
),
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info(f"Client disconnected")
|
||
|
||
@transport.event_handler("on_client_closed")
|
||
async def on_client_closed(transport, client):
|
||
logger.info(f"Client closed connection")
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=False)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from run import main
|
||
|
||
main()
|