127 lines
3.8 KiB
Python
127 lines
3.8 KiB
Python
#
|
||
# Copyright (c) 2024–2026, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import os
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.frames.frames import LLMRunFrame
|
||
from pipecat.pipeline.pipeline import Pipeline
|
||
from pipecat.pipeline.runner import PipelineRunner
|
||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||
from pipecat.processors.aggregators.llm_response_universal import (
|
||
LLMContextAggregatorPair,
|
||
LLMUserAggregatorParams,
|
||
)
|
||
from pipecat.runner.types import RunnerArguments
|
||
from pipecat.runner.utils import create_transport
|
||
from pipecat.services.camb.tts import CambTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.daily.transport import DailyParams
|
||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
# We use lambdas to defer transport parameter creation until the transport
|
||
# type is selected at runtime.
|
||
transport_params = {
|
||
"daily": lambda: DailyParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
),
|
||
}
|
||
|
||
|
||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||
logger.info("Starting Camb AI TTS bot")
|
||
|
||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
|
||
tts = CambTTSService(
|
||
api_key=os.getenv("CAMB_API_KEY"),
|
||
settings=CambTTSService.Settings(
|
||
model="mars-flash",
|
||
),
|
||
)
|
||
|
||
llm = OpenAILLMService(
|
||
api_key=os.getenv("OPENAI_API_KEY"),
|
||
settings=OpenAILLMService.Settings(
|
||
system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Keep responses concise.",
|
||
),
|
||
)
|
||
|
||
context = LLMContext()
|
||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||
context,
|
||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||
)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(),
|
||
stt,
|
||
user_aggregator,
|
||
llm,
|
||
tts,
|
||
transport.output(),
|
||
assistant_aggregator,
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
audio_out_sample_rate=22050,
|
||
),
|
||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info("Client connected")
|
||
context.add_message(
|
||
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||
)
|
||
await task.queue_frames([LLMRunFrame()])
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info("Client disconnected")
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
async def bot(runner_args: RunnerArguments):
|
||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||
transport = await create_transport(runner_args, transport_params)
|
||
await run_bot(transport, runner_args)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from pipecat.runner.run import main
|
||
|
||
main()
|