kanshan/xiaozhi-esp32
1
0
Fork 0
mirror of https://github.com/78/xiaozhi-esp32.git synced 2026-01-13 16:57:17 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
Build your own AI friend
738 Commits 7 Branches 67 Tags 370 MiB
C++ 74.6%
C 16%
Python 7.8%
CMake 1.4%
HTML 0.2%
764f6e3349
Go to file
小鹏 764f6e3349
Add wechat-mini-program support for otto-robot (#1444) 
* otto v1.4.0 MCP

1.使用MCP协议控制机器人
2.gif继承lcdDisplay，避免修改lcdDisplay

* otto v1.4.1 gif as components

gif as components

* electronBot v1.1.0 mcp

1.增加electronBot支持
2.mcp协议
3.gif 作为组件
4.display子类

* 规范代码

1.规范代码
2.修复切换主题死机bug

* fix(ota): 修复 ottoRobot和electronBot OTA 升级崩溃问题 bug

* 1.增加robot舵机初始位置校准
2.fix(mcp_sever) 超出范围异常捕获类型  bug

* refactor: Update Electron and Otto emoji display implementations

- Removed GIF selection from Kconfig for Electron and Otto boards.
- Updated Electron and Otto bot versions to 2.0.4 in their respective config files.
- Refactored emoji display classes to utilize EmojiCollection for managing emojis.
- Enhanced chat label setup and status display functionality in both classes.
- Cleaned up unused code and improved initialization logging for emoji displays.

* Rename OTTO_ICON_FONT.c to otto_icon_font.c

* Rename OTTO_ICON_FONT.c to otto_icon_font.c

* refactor: Update Otto emoji display configurations and functionalities

- Changed chat label text mode to circular scrolling for both Otto and Electron emoji displays.
- Bumped Otto robot version to 2.0.5 in the configuration file.
- Added new actions for Otto robot including Sit, WhirlwindLeg, Fitness, Greeting, Shy, RadioCalisthenics, MagicCircle, and Showcase.
- Enhanced servo sequence handling and added support for executing custom servo sequences.
- Improved logging and error handling for servo sequence execution.

* refactor: Update chat label long mode for Electron and Otto emoji displays

- Changed chat label text mode from wrap to circular scrolling for both Electron and Otto emoji displays.
- Improved consistency in chat label setup across both implementations.

* Update Otto robot README with new actions and parameters

* Update Otto controller parameters for oscillation settings

- Changed default oscillation period from 500ms to 300ms.
- Increased default steps from 5.0 to 8.0.
- Updated default amplitude from 20 degrees to 0 degrees.
- Enhanced documentation with new examples for oscillation modes and sequences.

* Fix default amplitude initialization in Otto controller to use a single zero instead of two digits.

* chore: update txp666/otto-emoji-gif-component version to 1.0.3 in idf_component.yml

* Refactor Otto controller
- Consolidated movement actions into a unified tool for the Otto robot, allowing for a single action command with various parameters.
- Removed individual movement tools (walk, turn, jump, etc.) and replaced them with a more flexible action system.

* Enhance Otto robot functionality by adding WebSocket control server and IP address retrieval feature. Updated config to support WebSocket, and revised README to include new control options and usage examples.
2025-11-17 22:26:58 +08:00
.github Refactor: Use esp_video component (#1245) 2025-10-14 10:44:45 +08:00
docs Update README (#1251) 2025-10-02 03:29:16 +08:00
main Add wechat-mini-program support for otto-robot (#1444) 2025-11-17 22:26:58 +08:00
partitions feat: build default assets instead of downloading and v2 tables for esp-hi, echoear (#1203) 2025-09-16 15:24:24 +08:00
scripts Revise README for ogg_converter clarity and instructions (#1432) 2025-11-15 13:11:35 +08:00
.gitignore Add esp32c5 configuration (#1258) 2025-10-05 09:59:28 +08:00
CMakeLists.txt Bump to 2.0.4 2025-10-25 04:21:46 +08:00
LICENSE Update LICENSE 2025-07-22 10:06:11 +08:00
README_en.md Update README (#1251) 2025-10-02 03:29:16 +08:00
README_ja.md Update README (#1251) 2025-10-02 03:29:16 +08:00
README.md Update README (#1251) 2025-10-02 03:29:16 +08:00
sdkconfig.defaults Fix lichuang-dev camera (#1290) 2025-10-14 20:44:44 +08:00
sdkconfig.defaults.esp32 Detect wake word model from index.json (#1211) 2025-09-17 08:31:51 +08:00
sdkconfig.defaults.esp32c3 Switch to 2.0 branch (#1152) 2025-09-04 15:41:28 +08:00
sdkconfig.defaults.esp32c5 Add esp32c5 configuration (#1258) 2025-10-05 09:59:28 +08:00
sdkconfig.defaults.esp32c6 Switch to 2.0 branch (#1152) 2025-09-04 15:41:28 +08:00
sdkconfig.defaults.esp32p4 feat: add camera support for M5Stack Tab5 (#1442) 2025-11-17 22:20:25 +08:00
sdkconfig.defaults.esp32s3 feat: build default assets instead of downloading and v2 tables for esp-hi, echoear (#1203) 2025-09-16 15:24:24 +08:00

README_en.md

An MCP-based Chatbot

(English | 中文 | 日本語)

Introduction

👉 Human: Give AI a camera vs AI: Instantly finds out the owner hasn't washed hair for three days【bilibili】

👉 Handcraft your AI girlfriend, beginner's guide【bilibili】

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

Version Notes

The current v2 version is incompatible with the v1 partition table, so it is not possible to upgrade from v1 to v2 via OTA. For partition table details, see partitions/v2/README.md.

All hardware running v1 can be upgraded to v2 by manually flashing the firmware.

The stable version of v1 is 1.9.2. You can switch to v1 by running git checkout v1. The v1 branch will be maintained until February 2026.

Features Implemented

  • Wi-Fi / ML307 Cat.1 4G
  • Offline voice wake-up ESP-SR
  • Supports two communication protocols (Websocket or MQTT+UDP)
  • Uses OPUS audio codec
  • Voice interaction based on streaming ASR + LLM + TTS architecture
  • Speaker recognition, identifies the current speaker 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.)
  • Customizable wake words, fonts, emojis, and chat backgrounds with online web-based editing (Custom Assets Generator)

Hardware

Breadboard DIY Practice

See the Feishu document tutorial:

👉 "XiaoZhi AI Chatbot Encyclopedia"

Breadboard demo:

Breadboard Demo

Supports 70+ Open Source Hardware (Partial List)

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 server by default. Personal users can register an account to use the Qwen real-time model for free.

👉 Beginner's Firmware Flashing Guide

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

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 console for configuration.

👉 Backend Operation Video Tutorial (Old Interface)

Related Open Source Projects

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

Other client projects using the XiaoZhi communication protocol:

Custom Assets Tools:

About the Project

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: 1011329060

Star History

Star History Chart