Files
pipecat/examples/update-settings/stt/stt-assemblyai.py
Aleix Conchillo Flaqué afa880f523 Deprecate passing a worker to PipelineRunner.run()
Register the worker with PipelineRunner.add_workers() before calling
run() instead. The worker argument still works but now emits a
DeprecationWarning and will be removed in a future release.

Update the runner docstrings, the run_test() helper, and all examples
(including the asyncio.gather() forms) to use the new pattern.
2026-05-21 23:02:33 -07:00

144 lines
4.6 KiB
Python

#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame, STTUpdateSettingsFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.worker import PipelineParams, PipelineWorker
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.assemblyai.stt import AssemblyAISTTService
from pipecat.services.cartesia.tts import CartesiaTTSService
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)
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(f"Starting bot")
stt = AssemblyAISTTService(
api_key=os.environ["ASSEMBLYAI_API_KEY"],
settings=AssemblyAISTTService.Settings(
model="u3-rt-pro",
),
)
tts = CartesiaTTSService(
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.environ["OPENAI_API_KEY"],
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Try saying difficult names like 'Xiomara', 'Saoirse', or 'Krzystof' to test transcription accuracy.",
),
)
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,
]
)
worker = PipelineWorker(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
logger.info(
"Phase 1: No keyterms boosting - try saying 'Xiomara', 'Saoirse', or 'Krzystof'"
)
context.add_message(
{"role": "developer", "content": "Please introduce yourself to the user."}
)
await worker.queue_frames([LLMRunFrame()])
await asyncio.sleep(15)
logger.info("🔄 Updating keyterms: Adding difficult names for boosting")
await worker.queue_frame(
STTUpdateSettingsFrame(
delta=AssemblyAISTTService.Settings(
keyterms_prompt=["Xiomara", "Saoirse", "Krzystof", "Nguyen", "Pipecat"]
)
)
)
logger.info("Phase 2: Keyterms active - same names should transcribe better now!")
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await worker.cancel()
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
await runner.add_workers(worker)
await runner.run()
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()