$git clone https://github.com/huangjunsen0406/py-xiaozhiEnglish | 简体中文
| 1 | # py-xiaozhi |
| 2 | |
| 3 | <p align="center" class="trendshift"> |
| 4 | <a href="https://trendshift.io/repositories/14130" target="_blank"> |
| 5 | <img src="https://trendshift.io/api/badge/repositories/14130" alt="Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/> |
| 6 | </a> |
| 7 | </p> |
| 8 | <p align="center"> |
| 9 | <a href="https://github.com/huangjunsen0406/py-xiaozhi/releases/latest"> |
| 10 | <img src="https://img.shields.io/github/v/release/huangjunsen0406/py-xiaozhi?style=flat-square&logo=github&color=blue" alt="Release"/> |
| 11 | </a> |
| 12 | <a href="https://opensource.org/licenses/MIT"> |
| 13 | <img src="https://img.shields.io/badge/License-MIT-green.svg?style=flat-square" alt="License: MIT"/> |
| 14 | </a> |
| 15 | <a href="https://github.com/huangjunsen0406/py-xiaozhi/stargazers"> |
| 16 | <img src="https://img.shields.io/github/stars/huangjunsen0406/py-xiaozhi?style=flat-square&logo=github" alt="Stars"/> |
| 17 | </a> |
| 18 | <a href="https://github.com/huangjunsen0406/py-xiaozhi/releases/latest"> |
| 19 | <img src="https://img.shields.io/github/downloads/huangjunsen0406/py-xiaozhi/total?style=flat-square&logo=github&color=52c41a1&maxAge=86400" alt="Download"/> |
| 20 | </a> |
| 21 | <a href="https://gitee.com/huang-jun-sen/py-xiaozhi"> |
| 22 | <img src="https://img.shields.io/badge/Gitee-FF5722?style=flat-square&logo=gitee" alt="Gitee"/> |
| 23 | </a> |
| 24 | <a href="https://huangjunsen0406.github.io/py-xiaozhi/guide/00_%E6%96%87%E6%A1%A3%E7%9B%AE%E5%BD%95.html"> |
| 25 | <img alt="Usage Docs" src="https://img.shields.io/badge/Usage Docs-View-blue?labelColor=2d2d2d" /> |
| 26 | </a> |
| 27 | <a href="https://atomgit.com/huangjunsen0406/py-xiaozhi"> |
| 28 | <img src="./assets/AtomGit.svg" alt="AtomGit" height="20"/> |
| 29 | </a> |
| 30 | </p> |
| 31 | |
| 32 | English | [简体中文](README.zh.md) |
| 33 | |
| 34 | ## ❤️ Sponsors |
| 35 | |
| 36 | > [Want to appear here?](mailto:huangjunsen0406@gmail.com) |
| 37 | |
| 38 | <details open> |
| 39 | <summary>Click to collapse</summary> |
| 40 | |
| 41 | [**GitDo.net**](https://gitdo.net/) |
| 42 | |
| 43 | Thanks to GitDo.net for sponsoring this project! GitDo.net is an AI API aggregation platform — one API Key for **Claude, Gemini, GPT** and other major models. Direct connection, no proxy needed, stable and efficient. An ideal choice for enterprise-grade AI programming. **[Visit GitDo.net](https://gitdo.net/)** |
| 44 | |
| 45 | --- |
| 46 | |
| 47 | | | | |
| 48 | |---|---| |
| 49 | | [**Token能量站**](https://factory.pub/register?aff=3rXc) | Thanks to Token能量站 (Factory.pub) for sponsoring this project! Providing API relay for **GPT, Grok, Claude** and other major models — stable, reliable, and affordable. **[Register here](https://factory.pub/register?aff=3rXc)** | |
| 50 | | [**良心AI**](https://www.openailaozu.com/register?aff=5Y7JEH5HBTXS) | Thanks to 良心AI for sponsoring this project! Providing API relay for **GPT, Claude, Gemini** and other major models — direct connection, stable and high-speed. **[Register here](https://www.openailaozu.com/register?aff=5Y7JEH5HBTXS)** | |
| 51 | |
| 52 | </details> |
| 53 | |
| 54 | ## About |
| 55 | |
| 56 | py-xiaozhi is a lightweight, cross-platform multi-modal AI interaction framework built on Python's async architecture. It supports real-time voice streaming, vision-language tasks, and IoT device control. Deployable across Windows, macOS, Linux desktops, and ARM embedded platforms (Raspberry Pi, Horizon Robotics RDK, Jetson Nano), it bridges the gap between Large Language Models and physical hardware — out of the box. |
| 57 | |
| 58 | > Evolved from the [xiaozhi-esp32](https://github.com/78/xiaozhi-esp32) firmware project. Officially adopted by [D-Robotics (xiaozhi-in-rdk)](https://github.com/D-Robotics/xiaozhi-in-rdk) as an upstream dependency. |
| 59 | |
| 60 | ## Related Projects |
| 61 | |
| 62 | - [xiaozhi-desktop](https://xiaozhi.junsen.online) — Electron desktop client with AEC echo cancellation, Live2D, floating window modes, and Windows / macOS installers |
| 63 | |
| 64 | ## Demo |
| 65 | |
| 66 | - [Bilibili Demo Video](https://www.bilibili.com/video/BV1HmPjeSED2/#reply255921347937) |
| 67 | |
| 68 |  |
| 69 | |
| 70 | ## Key Features |
| 71 | |
| 72 | - **Real-time Voice AI** — Opus codec with auto frame detection (RFC 6716 TOC parsing), async streaming, sub-20ms latency |
| 73 | - **Multi-modal Vision** — Camera capture + vision-language model integration for image understa |