> ## Documentation Index
> Fetch the complete documentation index at: https://docs.simli.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Pipecat

Pipecat is a realtime communication platform that allows you to create voice and video chat applications. Pipecat has it's own [documentation](https://docs.pipecat.ai/server/services/video/simli) for Simli, but we've included a guide below to get you started.

## Build your AI video agent with Pipecat

We recommend using Pipecat to run your Simli agent. below is a guide to set up your environment and dependencies.

1. **Create a new project**:

   ```bash theme={null}
   python3 -m venv .venv
   source .venv/bin/activate
   touch pipecat-simli.py
   ```

2. **Install dependencies**:

   ```bash theme={null}
   pip install "pipecat-ai[simli]"
   pip install "pipecat-ai[deepgram]"
   pip install "pipecat-ai[cartesia]"
   pip install "pipecat-ai[openai]"
   pip install "pipecat-ai[elevenlabs]"
   pip install "pipecat-ai[webrtc]"
   pip install fastapi dotenv loguru
   ... etc
   ```

3. **Set up your .env file**:
   Create a `.env` file in your project directory and add your api keys for Simli and other AI services. For example:

   ```bash .env theme={null}
   CARTESIA_API_KEY=...
   CARTESIA_VOICE_ID=...
   DEEPGRAM_API_KEY=...
   ELEVENLABS_API_KEY=...
   ELEVENLABS_VOICE_ID=...
   OPENAI_API_KEY=...
   SIMLI_API_KEY=...
   SIMLI_FACE_ID=...
   ```

4. **Fill in your Pipecat runner code**:
   Here's a simple example of a Pipecat runner file. Ensure your `.env` file is in the same directory as this file.

```python pipecat-simli.py theme={null}
import os

from dotenv import load_dotenv
from loguru import logger
from simli import SimliConfig

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.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.simli.video import SimliVideoService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.services.daily import DailyParams

load_dotenv(override=True)

transport_params = {
    "daily": lambda: DailyParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_out_enabled=True,
        video_out_is_live=True,
        video_out_width=512,
        video_out_height=512,
        vad_analyzer=SileroVADAnalyzer(),
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_out_enabled=True,
        video_out_is_live=True,
        video_out_width=512,
        video_out_height=512,
        vad_analyzer=SileroVADAnalyzer(),
    ),
}


async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    logger.info(f"Starting bot")

    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
        voice_id=os.getenv("CARTESIA_VOICE_ID"),
    )
    simli_ai = SimliVideoService(
        SimliConfig(os.getenv("SIMLI_API_KEY"), os.getenv("SIMLI_FACE_ID")),
    )


    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
    print("OPENAI_API_KEY:", os.getenv("OPENAI_API_KEY"))

    messages = [
        {
        "role": "system",
        "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way."
        },
    ]

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

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

    task = PipelineTask(
        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")
        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(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()
```

5. **Run your bot**:
   ```bash theme={null}
   python3 pipecat-simli.py
   ```
   and visit `http://localhost:7860` to talk to your agent in the Pipecat sandbox.
6. **Learn more**:
   For detailed documentation, visit [Pipecat's guide to Simli](https://docs.pipecat.ai/server/services/video/simli) or keep exploring Simli docs for more insights.