xiaozhi-esp32/README_en.md

# An MCP-based Chatbot

(English | [中文](README.md) | [日本語](README_ja.md))

## Video

👉 [Human: Give AI a camera vs AI: Instantly finds out the owner hasn't washed hair for three days【bilibili】](https://www.bilibili.com/video/BV1bpjgzKEhd/)

👉 [Handcraft your AI girlfriend, beginner's guide【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)

## Introduction

This is an open-source ESP32 project, released under the MIT license, allowing anyone to use it for free, including for commercial purposes.

We hope this project helps everyone understand AI hardware development and apply rapidly evolving large language models to real hardware devices.

If you have any ideas or suggestions, please feel free to raise Issues or join the QQ group: 575180511

### Control Everything with MCP

As a voice interaction entry, the XiaoZhi AI chatbot leverages the AI capabilities of large models like Qwen / DeepSeek, and achieves multi-terminal control via the MCP protocol.

![Control everything via MCP](docs/mcp-based-graph.jpg)

### Features Implemented

- Wi-Fi / ML307 Cat.1 4G
- Offline voice wake-up [ESP-SR](https://github.com/espressif/esp-sr)
- Supports two communication protocols ([Websocket](docs/websocket.md) or MQTT+UDP)
- Uses OPUS audio codec
- Voice interaction based on streaming ASR + LLM + TTS architecture
- Speaker recognition, identifies the current speaker [3D Speaker](https://github.com/modelscope/3D-Speaker)
- OLED / LCD display, supports emoji display
- Battery display and power management
- Multi-language support (Chinese, English, Japanese)
- Supports ESP32-C3, ESP32-S3, ESP32-P4 chip platforms
- Device-side MCP for device control (Speaker, LED, Servo, GPIO, etc.)
- Cloud-side MCP to extend large model capabilities (smart home control, PC desktop operation, knowledge search, email, etc.)

## Hardware

### Breadboard DIY Practice

See the Feishu document tutorial:

👉 ["XiaoZhi AI Chatbot Encyclopedia"](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)

Breadboard demo:

![Breadboard Demo](docs/v1/wiring2.jpg)

### Supports 70+ Open Source Hardware (Partial List)

- <a href="https://oshwhub.com/li-chuang-kai-fa-ban/li-chuang-shi-zhan-pai-esp32-s3-kai-fa-ban" target="_blank" title="LiChuang ESP32-S3 Development Board">LiChuang ESP32-S3 Development Board</a>
- <a href="https://github.com/espressif/esp-box" target="_blank" title="Espressif ESP32-S3-BOX3">Espressif ESP32-S3-BOX3</a>
- <a href="https://docs.m5stack.com/zh_CN/core/CoreS3" target="_blank" title="M5Stack CoreS3">M5Stack CoreS3</a>
- <a href="https://docs.m5stack.com/en/atom/Atomic%20Echo%20Base" target="_blank" title="AtomS3R + Echo Base">M5Stack AtomS3R + Echo Base</a>
- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="Magic Button 2.4">Magic Button 2.4</a>
- <a href="https://www.waveshare.net/shop/ESP32-S3-Touch-AMOLED-1.8.htm" target="_blank" title="Waveshare ESP32-S3-Touch-AMOLED-1.8">Waveshare ESP32-S3-Touch-AMOLED-1.8</a>
- <a href="https://github.com/Xinyuan-LilyGO/T-Circle-S3" target="_blank" title="LILYGO T-Circle-S3">LILYGO T-Circle-S3</a>
- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="XiaGe Mini C3">XiaGe Mini C3</a>
- <a href="https://oshwhub.com/movecall/cuican-ai-pendant-lights-up-y" target="_blank" title="Movecall CuiCan ESP32S3">CuiCan AI Pendant</a>
- <a href="https://github.com/WMnologo/xingzhi-ai" target="_blank" title="WMnologo-Xingzhi-1.54">WMnologo-Xingzhi-1.54TFT</a>
- <a href="https://www.seeedstudio.com/SenseCAP-Watcher-W1-A-p-5979.html" target="_blank" title="SenseCAP Watcher">SenseCAP Watcher</a>
- <a href="https://www.bilibili.com/video/BV1BHJtz6E2S/" target="_blank" title="ESP-HI Low Cost Robot Dog">ESP-HI Low Cost Robot Dog</a>

<div style="display: flex; justify-content: space-between;">
  <a href="docs/v1/lichuang-s3.jpg" target="_blank" title="LiChuang ESP32-S3 Development Board">
    <img src="docs/v1/lichuang-s3.jpg" width="240" />
  </a>
  <a href="docs/v1/espbox3.jpg" target="_blank" title="Espressif ESP32-S3-BOX3">
    <img src="docs/v1/espbox3.jpg" width="240" />
  </a>
  <a href="docs/v1/m5cores3.jpg" target="_blank" title="M5Stack CoreS3">
    <img src="docs/v1/m5cores3.jpg" width="240" />
  </a>
  <a href="docs/v1/atoms3r.jpg" target="_blank" title="AtomS3R + Echo Base">
    <img src="docs/v1/atoms3r.jpg" width="240" />
  </a>
  <a href="docs/v1/magiclick.jpg" target="_blank" title="Magic Button 2.4">
    <img src="docs/v1/magiclick.jpg" width="240" />
  </a>
  <a href="docs/v1/waveshare.jpg" target="_blank" title="Waveshare ESP32-S3-Touch-AMOLED-1.8">
    <img src="docs/v1/waveshare.jpg" width="240" />
  </a>
  <a href="docs/v1/lilygo-t-circle-s3.jpg" target="_blank" title="LILYGO T-Circle-S3">
    <img src="docs/v1/lilygo-t-circle-s3.jpg" width="240" />
  </a>
  <a href="docs/v1/xmini-c3.jpg" target="_blank" title="XiaGe Mini C3">
    <img src="docs/v1/xmini-c3.jpg" width="240" />
  </a>
  <a href="docs/v1/movecall-cuican-esp32s3.jpg" target="_blank" title="CuiCan">
    <img src="docs/v1/movecall-cuican-esp32s3.jpg" width="240" />
  </a>
  <a href="docs/v1/wmnologo_xingzhi_1.54.jpg" target="_blank" title="WMnologo-Xingzhi-1.54">
    <img src="docs/v1/wmnologo_xingzhi_1.54.jpg" width="240" />
  </a>
  <a href="docs/v1/sensecap_watcher.jpg" target="_blank" title="SenseCAP Watcher">
    <img src="docs/v1/sensecap_watcher.jpg" width="240" />
  </a>
  <a href="docs/v1/esp-hi.jpg" target="_blank" title="ESP-HI Low Cost Robot Dog">
    <img src="docs/v1/esp-hi.jpg" width="240" />
  </a>
</div>

## Software

### Firmware Flashing

For beginners, it is recommended to use the firmware that can be flashed without setting up a development environment.

The firmware connects to the official [xiaozhi.me](https://xiaozhi.me) server by default. Personal users can register an account to use the Qwen real-time model for free.

👉 [Beginner's Firmware Flashing Guide](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)

### Development Environment

- Cursor or VSCode
- Install ESP-IDF plugin, select SDK version 5.4 or above
- Linux is better than Windows for faster compilation and fewer driver issues
- This project uses Google C++ code style, please ensure compliance when submitting code

### Developer Documentation

- [Custom Board Guide](main/boards/README.md) - Learn how to create custom boards for XiaoZhi AI
- [MCP Protocol IoT Control Usage](docs/mcp-usage.md) - Learn how to control IoT devices via MCP protocol
- [MCP Protocol Interaction Flow](docs/mcp-protocol.md) - Device-side MCP protocol implementation
- [A detailed WebSocket communication protocol document](docs/websocket.md)

## Large Model Configuration

If you already have a XiaoZhi AI chatbot device and have connected to the official server, you can log in to the [xiaozhi.me](https://xiaozhi.me) console for configuration.

👉 [Backend Operation Video Tutorial (Old Interface)](https://www.bilibili.com/video/BV1jUCUY2EKM/)

## Related Open Source Projects

For server deployment on personal computers, refer to the following open-source projects:

- [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Python server
- [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Java server
- [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golang server

Other client projects using the XiaoZhi communication protocol:

- [huangjunsen0406/py-xiaozhi](https://github.com/huangjunsen0406/py-xiaozhi) Python client
- [TOM88812/xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) Android client

## Star History

<a href="https://star-history.com/#78/xiaozhi-esp32&Date">
 <picture>
   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date&theme=dark" />
   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
 </picture>
</a>