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

# Pipecat

> Open source Python framework for building voice and multimodal AI agents.

Pipecat is an open source Python framework for building voice and multimodal AI agents. It orchestrates AI services, network transports, and audio processing to enable ultra-low latency conversations that feel natural and responsive.

<Card title="Quickstart" icon="rocket" href="/pipecat/get-started/quickstart">
  Want to dive right in? Build and run your first Pipecat application
</Card>

## What You Can Build

<CardGroup cols={3}>
  <Card title="Voice Assistants" icon="microphone" href="https://github.com/pipecat-ai/pipecat-examples/tree/main/simple-chatbot">
    Natural, real-time conversations with AI using speech recognition and
    synthesis
  </Card>

  <Card title="Phone Agents" icon="phone" href="https://github.com/pipecat-ai/pipecat-examples/tree/main/twilio-chatbot">
    Connect to your agent via phone for support, intake, and customer service
    interactions
  </Card>

  <Card title="Multimodal Apps" icon="layer-group" href="https://github.com/pipecat-ai/pipecat/blob/main/examples/vision/vision-openai.py">
    Applications that combine voice, video, images, and text for rich interactions
  </Card>

  <Card title="Creative Experiences" icon="wand-magic-sparkles" href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot">
    Storytelling experiences and social companions that engage users
  </Card>

  <Card title="Interactive Games" icon="gamepad" href="https://github.com/pipecat-ai/pipecat-examples/tree/main/word-wrangler-gemini-live">
    Voice-controlled games and interactive experiences with real-time AI responses
  </Card>

  <Card title="Conversation Flows" icon="diagram-project" href="/pipecat-flows/introduction">
    Build structured conversations with Pipecat Flows to complete tasks and improve LLM accuracy
  </Card>
</CardGroup>

## How It Works

Pipecat orchestrates AI services in a **pipeline**, which is a series of processors that handle real-time audio, text, and video frames with ultra-low latency.

Here's what happens in a typical voice conversation:

1. **Transport** receives audio from the user (browser, phone, etc.)
2. **Speech Recognition** converts speech to text in real-time
3. **LLM** generates intelligent responses based on context
4. **Speech Synthesis** converts responses back to natural speech
5. **Transport** streams audio back to the user

In most cases, the entire round-trip interaction happens between 500-800ms, creating a natural conversation experience for the user.

<img src="https://mintcdn.com/daily/2bYrACcmgvvzC075/images/pipecat-overview.png?fit=max&auto=format&n=2bYrACcmgvvzC075&q=85&s=662989d7a789021f9cd8742df91dc508" alt="Pipecat Overview" className="rounded-lg" width="2320" height="1660" data-path="images/pipecat-overview.png" />

## Ready to Build?

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/pipecat/get-started/quickstart">
    Build and run your first Pipecat application
  </Card>

  <Card title="Core Concepts" icon="book-open" href="/pipecat/learn/overview">
    Learn about pipelines, processors, transports, and context management
  </Card>

  <Card title="Supported Services" icon="puzzle-piece" href="/api-reference/server/services/supported-services">
    Browse the complete list of 100+ AI service integrations
  </Card>

  <Card title="Deploy" icon="cloud" href="/pipecat/deployment/overview">
    Deploy to Pipecat Cloud or self-host on your own infrastructure
  </Card>
</CardGroup>