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

# Pipecat

PipeCat is an open-source Python framework that handles complex orchestration of AI services, network transport, audio processing, and multimodal interactions.

Learn to use the SambaNova LLM and Speech-to-text(STT) integrations and try the example use cases for building real-time speech applications.

## Prerequisites

* A [SambaCloud](https://cloud.sambanova.ai) account and API key.
* Ensure Python version 3.11 or 3.12 is installed locally.
* A PipeCat-compatible STT provider key (e.g., [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia)).
* `.env` file with all your API keys in your working directory.

### Install dependencies

```bash
pip install python-dotenv fastapi uvicorn
pip install pipecat-ai-small-webrtc-prebuilt
pip install pipecat-ai[sambanova, webrtc, silero, daily]
```

## Usage

You can integrate SambaNova’s STT and LLM services into your Pipecat pipeline as shown below:

```python
from pipecat.services.sambanova.llm import SambaNovaLLMService
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transcriptions.language import Language
from pipecat.pipeline.pipeline import Pipeline

# Instantiate SambaNova services
sambanova_llm = SambaNovaLLMService(
    api_key='your-sambanova-api-key',
    model='Llama-4-Maverick-17B-128E-Instruct',
    params=SambaNovaLLMService.InputParams(
        temperature=0.7,
        max_tokens=1024
    )
)

sambanova_stt = SambaNovaSTTService(
    model="Whisper-Large-v3",
    api_key="your-sambanova-api-key",
    language=Language.EN,
    prompt="Transcribe the following conversation",
    temperature=0.0
)

# Add the SambaNova models to your pipeline
pipeline = Pipeline([
    transport.input(),
    sambanova_stt,
    ...
    sambanova_llm,
    tts,
    transport.output(),
    ...
])
```

Follow the [integrations example](https://github.com/sambanova/integrations/tree/main/pipecat_integration) to build and deploy a real-time speech-to-speech weather agent.

## Learn more

* [SambaNova Cloud signup](https://cloud.sambanova.ai/signup) – Get started with your free API key.
* [SambaNova API reference](/en/api-reference/overview) – Explore supported models, endpoints, and parameters.
* [SambaNova Pipecat LLM docs](https://docs.pipecat.ai/server/services/llm/sambanova) –Learn how to integrate LLM services.
* [SambaNova Pipecat STT docs](https://docs.pipecat.ai/server/services/stt/sambanova) – Configure speech-to-text using SambaNova models.
* [Pipecat guides](https://docs.pipecat.ai/guides/introduction) – Browse examples like the weather agent and build your own.