958517b931
* audio interrupt * support esp launchpad online download * Update config.toml config url * Update README.md 新窗口打开 * Update config.toml * Update config.toml * Update config.toml * Update README.md * Update config.toml * Update config.toml * Update config.toml * fix config file and bin name error fix config file and bin name error * add Esp Launchpad in readme * Update config.toml * update readme * fit all board online download * Update config.toml firmware url to releases * Update README.md * Update README_en.md * Revert "Update config.toml" This reverts commit1fe349d5b4. * Revert "Update README.md" This reverts commit8fc7dc8e68. * Revert "Update README_en.md" This reverts commit346ab09b90. * 增加esp SparkBot * sparkbot work ok * Update config.h * delete esp launchpad * Update application.cc * esp-sparkbot picture * Resolve display io and PA io conflicts on Esp Sparkbot board * Update CMakeLists.txt Keep the board type consistent with the folder name. --------- Co-authored-by: Xiaoxia <terrence@tenclass.com>
XiaoZhi AI Chatbot
This is Terrence's first hardware project.
👉 Build your AI chat companion with ESP32+SenseVoice+Qwen72B! [bilibili]
👉 DIY Your AI Companion - Beginner's Tutorial [bilibili]
Project Purpose
This project is developed based on Espressif's ESP-IDF.
This is an open-source project primarily for educational purposes. Through this project, we aim to help more people get started with AI hardware development and understand how to integrate rapidly evolving large language models into actual hardware devices. Whether you're a student interested in AI or a developer looking to explore new technologies, this project offers valuable learning experiences.
Everyone is welcome to participate in the project's development and improvement. If you have any ideas or suggestions, please feel free to raise an Issue or join our chat group.
Learning & Discussion QQ Group: 946599635
Implemented Features
- Wi-Fi / ML307 Cat.1 4G
- BOOT button wake-up and interrupt, supporting both click and long-press triggers
- Offline voice wake-up ESP-SR
- Streaming voice dialogue (WebSocket or UDP protocol)
- Support for 5 languages: Mandarin, Cantonese, English, Japanese, Korean SenseVoice
- Voice print recognition to identify who's calling AI's name 3D Speaker
- Large model TTS (Volcengine or CosyVoice)
- Large Language Model (Qwen2.5 72B or Doubao API)
- Configurable prompts and voice tones (custom characters)
- Short-term memory with self-summary after each conversation round
- OLED / LCD display showing signal strength or conversation content
Hardware Section
Breadboard Practice
For detailed tutorial, see the Feishu document:
👉 XiaoZhi AI Chatbot Encyclopedia
Breadboard setup shown below:
Supported Open-Source Hardware
- LiChuang ESP32-S3 Development Board
- Espressif ESP32-S3-BOX3
- M5Stack CoreS3
- AtomS3R + Echo Base
- MagiClick 2.4
- Xmini C3
- Waveshare ESP32-S3-Touch-AMOLED-1.8
Firmware Section
Flashing Without Development Environment
For beginners, it's recommended to first try flashing the firmware without setting up a development environment. The firmware uses a test server provided by the author, currently available for free use (not for commercial purposes).
👉 Flash Firmware Guide (No IDF Environment Required)
Development Environment
- Cursor or VSCode
- Install ESP-IDF plugin, select SDK version 5.3 or above
- Linux is preferred over Windows for faster compilation and fewer driver issues
AI Character Configuration
If you already have a XiaoZhi AI chatbot, please refer to 👉 Backend Operation Video Tutorial
For detailed usage instructions and test server notes, please refer to 👉 XiaoZhi Test Server Help Guide.