DailyTransport, Gladia, Tagalog / English mixed

gladia-tagalog-mixed.py

#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import argparse
import asyncio
import os

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.stt import OpenAISTTService
from pipecat.services.openai.tts import OpenAITTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
from pipecat.transports.services.daily import DailyParams, DailyTransport

load_dotenv(override=True)


async def run_bot():
    logger.info(f"Starting bot")

    transport = DailyTransport(
        os.getenv("DAILY_ROOM_URL"),
        os.getenv("DAILY_TOKEN"),
        "Respond bot",
        params=DailyParams(
            audio_in_enabled=True,
            audio_out_enabled=True,
            transcription_enabled=False,
            vad_audio_passthrough=True,
            vad_enabled=True,
            vad_analyzer=SileroVADAnalyzer(),
        ),
    )

    stt = GladiaSTTService(
        api_key=os.getenv("GLADIA_API_KEY"),
        params=GladiaInputParams(
            language_config=LanguageConfig(
                languages=[Language.EN, Language.TL],
            )
        ),
    )

    tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")

    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))

    messages = [
        {
            "role": "system",
            "content": "If the user says something in English, respond in English. If the user says something in Tagalog, say: 'Hey, that's Tagalog.', and then respond in Tagalog.",
        },
    ]

    context = OpenAILLMContext(messages)
    context_aggregator = llm.create_context_aggregator(context)

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,  # STT
            context_aggregator.user(),  # User responses
            llm,  # LLM
            tts,  # TTS
            transport.output(),  # Transport bot output
            context_aggregator.assistant(),  # Assistant spoken responses
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            allow_interruptions=True,
            audio_out_sample_rate=24000,
            enable_metrics=True,
            enable_usage_metrics=True,
            report_only_initial_ttfb=True,
        ),
    )

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
        messages.append({"role": "user", "content": "Say 'ready'"})
        await task.queue_frames([context_aggregator.user().get_context_frame()])

    @transport.event_handler("on_client_disconnected")
    async def on_client_disconnected(transport, client):
        logger.info(f"Client disconnected")
        await task.cancel()

    runner = PipelineRunner()

    await runner.run(task)


if __name__ == "__main__":
    asyncio.run(run_bot())