> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/yocxy2/chatterboxyocxy/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> State-of-the-art open-source text-to-speech models with zero-shot voice cloning and multilingual support

# Chatterbox TTS

Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI. Built for developers who need high-quality, low-latency speech synthesis with zero-shot voice cloning capabilities.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get up and running with Chatterbox in minutes
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install Chatterbox via pip or from source
  </Card>

  <Card title="Models Overview" icon="brain" href="/models/chatterbox-turbo">
    Explore our three optimized TTS models
  </Card>

  <Card title="API Reference" icon="code" href="/api/chatterbox-turbo-tts">
    Complete API documentation
  </Card>
</CardGroup>

## Key Features

<CardGroup cols={2}>
  <Card title="Zero-Shot Voice Cloning" icon="microphone">
    Clone any voice with just 3-10 seconds of reference audio
  </Card>

  <Card title="Paralinguistic Tags" icon="face-laugh">
    Add realism with \[laugh], \[chuckle], \[cough], and more
  </Card>

  <Card title="23+ Languages" icon="globe">
    Multilingual support for global applications
  </Card>

  <Card title="Built-in Watermarking" icon="shield-check">
    Responsible AI with Perth watermarking technology
  </Card>
</CardGroup>

## Model Zoo

Choose the right model for your application:

| Model                   | Size | Languages | Key Features                                | Best For                                     |
| ----------------------- | ---- | --------- | ------------------------------------------- | -------------------------------------------- |
| **Chatterbox-Turbo**    | 350M | English   | Paralinguistic tags, lower compute and VRAM | Zero-shot voice agents, production           |
| Chatterbox-Multilingual | 500M | 23+       | Zero-shot cloning, multiple languages       | Global applications, localization            |
| Chatterbox              | 500M | English   | CFG & exaggeration tuning                   | General zero-shot TTS with creative controls |

<Note>
  **Chatterbox-Turbo** is our most efficient model yet. Built on a streamlined 350M parameter architecture, it delivers high-quality speech with less compute and just **one decoding step** (down from 10).
</Note>

## Getting Started

<Steps>
  <Step title="Install Chatterbox">
    Install via pip in under a minute:

    ```bash theme={null}
    pip install chatterbox-tts
    ```
  </Step>

  <Step title="Load a Model">
    Choose from Turbo, Original, or Multilingual models:

    ```python theme={null}
    from chatterbox.tts_turbo import ChatterboxTurboTTS

    model = ChatterboxTurboTTS.from_pretrained(device="cuda")
    ```
  </Step>

  <Step title="Generate Speech">
    Create natural-sounding speech with paralinguistic tags:

    ```python theme={null}
    text = "Hi there! [chuckle] Ready to get started?"
    wav = model.generate(text)
    ```
  </Step>
</Steps>

## Live Demos

Try Chatterbox models online:

<CardGroup cols={2}>
  <Card title="Chatterbox-Turbo Demo" icon="bolt" href="https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo">
    Experience the fastest model with paralinguistic tags
  </Card>

  <Card title="Multilingual Demo" icon="language" href="https://huggingface.co/spaces/ResembleAI/Chatterbox-Multilingual-TTS">
    Test 23+ language support
  </Card>

  <Card title="Listen to Samples" icon="headphones" href="https://resemble-ai.github.io/chatterbox_turbo_demopage/">
    Hear quality examples from all models
  </Card>

  <Card title="Join Discord" icon="discord" href="https://discord.gg/rJq9cRJBJ6">
    Connect with the community
  </Card>
</CardGroup>

## Use Cases

Chatterbox excels at:

* **Voice Agents**: Low-latency conversational AI with natural prosody
* **Narration**: Audiobooks, podcasts, and content creation
* **Localization**: Multi-language content for global audiences
* **Accessibility**: Text-to-speech for visually impaired users
* **Game Development**: Dynamic character voices and dialogue
* **Virtual Assistants**: Natural-sounding voice interfaces

## Community & Support

<CardGroup cols={3}>
  <Card title="GitHub" icon="github" href="https://github.com/yocxy2/chatterboxyocxy">
    Star the repository
  </Card>

  <Card title="Discord" icon="discord" href="https://discord.gg/rJq9cRJBJ6">
    Join our community
  </Card>

  <Card title="Resemble AI" icon="building" href="https://resemble.ai">
    Enterprise solutions
  </Card>
</CardGroup>

<Note>
  Made with ♥️ by [Resemble AI](https://resemble.ai). If you need production-ready TTS with sub-200ms latency and enterprise support, check out our competitively priced service.
</Note>