Pipecat integration

pip install pipecat-shunyalabs

pip install pipecat-shunyalabs pipecat-ai[daily]

export SHUNYALABS_API_KEY="your-api-key"

stt = ShunyalabsSTTService(api_key="your-api-key")
tts = ShunyalabsTTSService(api_key="your-api-key")

import asyncio, os
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.local.audio import LocalAudioTransport
from pipecat_shunyalabs import ShunyalabsSTTService, ShunyalabsTTSService

async def main():
    transport = LocalAudioTransport()

    stt = ShunyalabsSTTService(
        api_key=os.environ["SHUNYALABS_API_KEY"],
        language="en",
    )

    llm = OpenAILLMService(
        api_key=os.environ["OPENAI_API_KEY"],
        model="gpt-4o",
    )

    tts = ShunyalabsTTSService(
        api_key=os.environ["SHUNYALABS_API_KEY"],
        voice="Rajesh",
        language="en",
        style="<Conversational>",
    )

    pipeline = Pipeline([transport.input(), stt, llm, tts, transport.output()])
    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
    await PipelineRunner().run(task)

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

from pipecat_shunyalabs import ShunyalabsSTTService

stt = ShunyalabsSTTService(
    language="hi",       # Hindi; use "auto" for detection
    sample_rate=16000,
)

tts = ShunyalabsTTSService(speaker="Rajesh", style="<Happy>")
# Input:  "Welcome!"
# Sent:   "<Happy> Welcome!"

import asyncio, os
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, OpenAILLMContextAggregator,
)
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat_shunyalabs import ShunyalabsSTTService, ShunyalabsTTSService

async def run_voice_agent(room_url: str, token: str):
    transport = DailyTransport(
        room_url, token, "Shunyalabs Agent",
        DailyParams(audio_out_enabled=True, transcription_enabled=False),
    )

    stt = ShunyalabsSTTService(
        api_key=os.environ["SHUNYALABS_API_KEY"],
        language="auto",
        sample_rate=16000,
    )

    llm = OpenAILLMService(
        api_key=os.environ["OPENAI_API_KEY"],
        model="gpt-4o",
    )

    messages = [{"role": "system", "content": "You are a helpful voice assistant."}]
    context = OpenAILLMContext(messages)
    context_aggregator = llm.create_context_aggregator(context)

    tts = ShunyalabsTTSService(
        api_key=os.environ["SHUNYALABS_API_KEY"],
        voice="Rajesh",
        language="hi",
        style="<Conversational>",
    )

    pipeline = Pipeline([
        transport.input(),
        stt,
        context_aggregator.user(),
        llm,
        tts,
        transport.output(),
        context_aggregator.assistant(),
    ])

    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))

    @transport.event_handler("on_first_participant_joined")
    async def on_first_participant_joined(transport, participant):
        await task.queue_frames([context_aggregator.user().get_context_frame()])

    await PipelineRunner().run(task)

if __name__ == "__main__":
    asyncio.run(run_voice_agent(
        room_url=os.environ["DAILY_ROOM_URL"],
        token=os.environ["DAILY_TOKEN"],
    ))

# Hindi conversational bot
tts = ShunyalabsTTSService(voice="Rajesh", language="hi", style="<Conversational>")

# English news-style bot
tts = ShunyalabsTTSService(voice="Varun", language="en", style="<News>")