Universal 3.5 Pro Realtime on Pipecat

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.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.workers.runner import WorkerRunner

load_dotenv()

transport_params = {
    "daily": lambda: DailyParams(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):
    stt = AssemblyAISTTService(
        api_key=os.environ["ASSEMBLYAI_API_KEY"],
        settings=AssemblyAISTTService.Settings(
            model="universal-3-5-pro",
            min_turn_silence=100,
            # max_turn_silence is auto-synced to min_turn_silence in Pipecat mode.
            # vad_threshold=0.3,            # Align with your local VAD's threshold
            # continuous_partials=True,     # Default — steady ~3s partials during long turns
            # interruption_delay=0,         # Optional: faster first partial (~300ms effective)
        ),
        vad_force_turn_endpoint=True,  # Pipecat mode (default).
        # Set False to use AssemblyAI's built-in turn detection (u3-rt-pro / universal-3-5-pro only):
        # vad_force_turn_endpoint=False,
    )

    llm = OpenAILLMService(api_key=os.environ["OPENAI_API_KEY"])
    tts = CartesiaTTSService(api_key=os.environ["CARTESIA_API_KEY"])

    context = LLMContext()
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
    )

    pipeline = Pipeline(
        [
            transport.input(),     # Transport user input
            stt,                   # STT
            user_aggregator,       # User responses
            llm,                   # LLM
            tts,                   # TTS
            transport.output(),    # Transport bot output
            assistant_aggregator,  # Assistant responses → automatic conversation context
        ]
    )

    worker = PipelineWorker(pipeline, params=PipelineParams(enable_metrics=True))

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        context.add_message(
            {"role": "system", "content": "You are a helpful voice assistant. Keep replies brief and speakable."}
        )
        await worker.queue_frames([LLMRunFrame()])

    runner = WorkerRunner(handle_sigint=runner_args.handle_sigint)
    await runner.add_workers(worker)
    await runner.run()


async def bot(runner_args: RunnerArguments):
    transport = await create_transport(runner_args, transport_params)
    await run_bot(transport, runner_args)


if __name__ == "__main__":
    from pipecat.runner.run import main

    main()