Skip to content

Commit d0e3426

Browse files
committed
Update docs
1 parent 1d1fe3d commit d0e3426

File tree

4 files changed

+447
-75
lines changed

4 files changed

+447
-75
lines changed

README.md

+19-10
Original file line numberDiff line numberDiff line change
@@ -4,15 +4,17 @@
44

55
这是虾哥的第一个硬件作品。
66

7-
👉 [ESP32+SenseVoice+Qwen72B打造你的AI聊天伴侣!【bilibili】](https://www.bilibili.com/video/BV11msTenEH3/?share_source=copy_web&vd_source=ee1aafe19d6e60cf22e60a93881faeba)
7+
👉 [ESP32+SenseVoice+Qwen72B打造你的AI聊天伴侣!【bilibili】](https://www.bilibili.com/video/BV11msTenEH3/)
8+
9+
👉 [给小智装上 DeepSeek 的聪明大脑【bilibili】](https://www.bilibili.com/video/BV1GQP6eNEFG/)
810

911
👉 [手工打造你的 AI 女友,新手入门教程【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)
1012

1113
## 项目目的
1214

13-
本项目基于乐鑫的 ESP-IDF 进行开发
15+
本项目是一个开源项目,以 MIT 许可证发布,允许任何人免费使用,并可以用于商业用途
1416

15-
本项目是一个开源项目,主要用于教学目的。我们希望通过这个项目,能够帮助更多人入门 AI 硬件开发,了解如何将当下飞速发展的大语言模型应用到实际的硬件设备中。无论你是对 AI 感兴趣的学生,还是想要探索新技术的开发者,都可以通过这个项目获得宝贵的学习经验。
17+
我们希望通过这个项目,能够帮助更多人入门 AI 硬件开发,了解如何将当下飞速发展的大语言模型应用到实际的硬件设备中。无论你是对 AI 感兴趣的学生,还是想要探索新技术的开发者,都可以通过这个项目获得宝贵的学习经验。
1618

1719
欢迎所有人参与到项目的开发和改进中来。如果你有任何想法或建议,请随时提出 Issue 或加入群聊。
1820

@@ -32,6 +34,7 @@
3234
- 短期记忆,每轮对话后自我总结
3335
- OLED / LCD 显示屏,显示信号强弱或对话内容
3436
- 支持 LCD 显示图片表情
37+
- 支持多语言(中文、英文)
3538

3639
## 硬件部分
3740

@@ -71,9 +74,6 @@
7174
<a href="docs/v1/atoms3r.jpg" target="_blank" title="AtomS3R + Echo Base">
7275
<img src="docs/v1/atoms3r.jpg" width="240" />
7376
</a>
74-
<a href="docs/AtomMatrix-echo-base.jpg" target="_blank" title="AtomMatrix-echo-base + Echo Base">
75-
<img src="docs/AtomMatrix-echo-base.jpg" width="240" />
76-
</a>
7777
<a href="docs/v1/magiclick.jpg" target="_blank" title="神奇按钮 2.4">
7878
<img src="docs/v1/magiclick.jpg" width="240" />
7979
</a>
@@ -95,7 +95,9 @@
9595

9696
### 免开发环境烧录
9797

98-
新手第一次操作建议先不要搭建开发环境,直接使用免开发环境烧录的固件。固件使用的是作者友情提供的测试服,目前开放免费使用,请勿用于商业用途。
98+
新手第一次操作建议先不要搭建开发环境,直接使用免开发环境烧录的固件。
99+
100+
固件默认接入 [xiaozhi.me](https://xiaozhi.me) 官方服务器,目前个人用户注册账号可以免费使用 Qwen 实时模型。
99101

100102
👉 [Flash烧录固件(无IDF开发环境)](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
101103

@@ -105,13 +107,20 @@
105107
- Cursor 或 VSCode
106108
- 安装 ESP-IDF 插件,选择 SDK 版本 5.3 或以上
107109
- Linux 比 Windows 更好,编译速度快,也免去驱动问题的困扰
110+
- 使用 Google C++ 代码风格,提交代码时请确保符合规范
111+
112+
113+
## 智能体配置
114+
115+
如果你已经拥有一个小智 AI 聊天机器人设备,可以登录 [xiaozhi.me](https://xiaozhi.me) 控制台进行配置。
108116

117+
👉 [后台操作视频教程(旧版界面)](https://www.bilibili.com/video/BV1jUCUY2EKM/)
109118

110-
## AI 角色配置
119+
## 技术原理与私有化部署
111120

112-
如果你已经拥有一个小智 AI 聊天机器人,可以参考 👉 [后台操作视频教程](https://www.bilibili.com/video/BV1jUCUY2EKM/)
121+
👉 [一份详细的 WebSocket 通信协议文档](docs/websocket.md)
113122

114-
详细的使用说明以及测试服的注意事项,请参考 👉 [小智测试服的帮助说明](https://xiaozhi.me/help)
123+
在个人电脑上部署服务器,可以参考另一位作者同样以 MIT 许可证开源的项目 [xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server)
115124

116125
## Star History
117126

README_en.md

+36-24
Original file line numberDiff line numberDiff line change
@@ -1,62 +1,65 @@
11
# XiaoZhi AI Chatbot
22

3-
[中文](README.md) | English | [日本語](README_ja.md)
3+
([中文](README.md) | English | [日本語](README_ja.md))
44

55
This is Terrence's first hardware project.
66

7-
👉 [Build your AI chat companion with ESP32+SenseVoice+Qwen72B! [bilibili]](https://www.bilibili.com/video/BV11msTenEH3/?share_source=copy_web&vd_source=ee1aafe19d6e60cf22e60a93881faeba)
7+
👉 [Build your AI chat companion with ESP32+SenseVoice+Qwen72B!bilibili](https://www.bilibili.com/video/BV11msTenEH3/)
88

9-
👉 [DIY Your AI Companion - Beginner's Tutorial [bilibili]](https://www.bilibili.com/video/BV1XnmFYLEJN/)
9+
👉 [Equipping XiaoZhi with DeepSeek's smart brain【bilibili】](https://www.bilibili.com/video/BV1GQP6eNEFG/)
10+
11+
👉 [Build your own AI companion, a beginner's guide【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)
1012

1113
## Project Purpose
1214

13-
This project is developed based on Espressif's ESP-IDF.
15+
This is an open-source project released under the MIT license, allowing anyone to use it freely, including for commercial purposes.
1416

15-
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.
17+
Through this project, we aim to help more people get started with AI hardware development and understand how to implement rapidly evolving large language models in actual hardware devices. Whether you're a student interested in AI or a developer exploring new technologies, this project offers valuable learning experiences.
1618

17-
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.
19+
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 the chat group.
1820

1921
Learning & Discussion QQ Group: 946599635
2022

2123
## Implemented Features
2224

2325
- Wi-Fi / ML307 Cat.1 4G
24-
- BOOT button wake-up and interrupt, supporting both click and long-press triggers
26+
- BOOT button wake-up and interruption, supporting both click and long-press triggers
2527
- Offline voice wake-up [ESP-SR](https://github.com/espressif/esp-sr)
2628
- Streaming voice dialogue (WebSocket or UDP protocol)
2729
- Support for 5 languages: Mandarin, Cantonese, English, Japanese, Korean [SenseVoice](https://github.com/FunAudioLLM/SenseVoice)
2830
- Voice print recognition to identify who's calling AI's name [3D Speaker](https://github.com/modelscope/3D-Speaker)
29-
- Large model TTS (Volcengine or CosyVoice)
30-
- Large Language Model (Qwen2.5 72B or Doubao API)
31+
- Large model TTS (Volcano Engine or CosyVoice)
32+
- Large Language Models (Qwen, DeepSeek, Doubao)
3133
- Configurable prompts and voice tones (custom characters)
32-
- Short-term memory with self-summary after each conversation round
34+
- Short-term memory, self-summarizing after each conversation round
3335
- OLED / LCD display showing signal strength or conversation content
34-
- Support for displaying emoji images on LCD
36+
- Support for LCD image expressions
37+
- Multi-language support (Chinese, English)
3538

3639
## Hardware Section
3740

38-
### Breadboard Practice
41+
### Breadboard DIY Practice
3942

40-
For detailed tutorial, see the Feishu document:
43+
See the Feishu document tutorial:
4144

4245
👉 [XiaoZhi AI Chatbot Encyclopedia](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)
4346

44-
Breadboard setup shown below:
47+
Breadboard demonstration:
4548

46-
![Breadboard Setup](docs/wiring2.jpg)
49+
![Breadboard Demo](docs/wiring2.jpg)
4750

48-
### Supported Open-Source Hardware
51+
### Supported Open Source Hardware
4952

5053
- <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>
5154
- <a href="https://github.com/espressif/esp-box" target="_blank" title="Espressif ESP32-S3-BOX3">Espressif ESP32-S3-BOX3</a>
5255
- <a href="https://docs.m5stack.com/zh_CN/core/CoreS3" target="_blank" title="M5Stack CoreS3">M5Stack CoreS3</a>
5356
- <a href="https://docs.m5stack.com/en/atom/Atomic%20Echo%20Base" target="_blank" title="AtomS3R + Echo Base">AtomS3R + Echo Base</a>
5457
- <a href="https://docs.m5stack.com/en/core/ATOM%20Matrix" target="_blank" title="AtomMatrix + Echo Base">AtomMatrix + Echo Base</a>
55-
- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="MagiClick 2.4">MagiClick 2.4</a>
58+
- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="Magic Button 2.4">Magic Button 2.4</a>
5659
- <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>
5760
- <a href="https://github.com/Xinyuan-LilyGO/T-Circle-S3" target="_blank" title="LILYGO T-Circle-S3">LILYGO T-Circle-S3</a>
58-
- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="Xmini C3">Xmini C3</a>
59-
- <a href="https://oshwhub.com/movecall/moji-xiaozhi-ai-derivative-editi" target="_blank" title="Movecall Moji ESP32S3">Movecall Moji ESP32S3</a>
61+
- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="XiaGe Mini C3">XiaGe Mini C3</a>
62+
- <a href="https://oshwhub.com/movecall/moji-xiaozhi-ai-derivative-editi" target="_blank" title="Movecall Moji ESP32S3">Moji XiaoZhi AI Derivative Version</a>
6063

6164
<div style="display: flex; justify-content: space-between;">
6265
<a href="docs/v1/lichuang-s3.jpg" target="_blank" title="LiChuang ESP32-S3 Development Board">
@@ -95,21 +98,30 @@ Breadboard setup shown below:
9598

9699
### Flashing Without Development Environment
97100

98-
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).
101+
For beginners, it's recommended to first use the firmware that can be flashed without setting up a development environment.
102+
103+
The firmware connects to the official [xiaozhi.me](https://xiaozhi.me) server by default. Currently, personal users can register an account to use the Qwen real-time model for free.
99104

100-
👉 [Flash Firmware Guide (No IDF Environment Required)](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
105+
👉 [Flash Firmware Guide (No IDF Environment)](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
101106

102107
### Development Environment
103108

104109
- Cursor or VSCode
105110
- Install ESP-IDF plugin, select SDK version 5.3 or above
106111
- Linux is preferred over Windows for faster compilation and fewer driver issues
112+
- Use Google C++ code style, ensure compliance when submitting code
113+
114+
## AI Agent Configuration
115+
116+
If you already have a XiaoZhi AI chatbot device, you can configure it through the [xiaozhi.me](https://xiaozhi.me) console.
117+
118+
👉 [Backend Operation Tutorial (Old Interface)](https://www.bilibili.com/video/BV1jUCUY2EKM/)
107119

108-
## AI Character Configuration
120+
## Technical Principles and Private Deployment
109121

110-
If you already have a XiaoZhi AI chatbot, please refer to 👉 [Backend Operation Video Tutorial](https://www.bilibili.com/video/BV1jUCUY2EKM/)
122+
👉 [Detailed WebSocket Communication Protocol Documentation](docs/websocket.md)
111123

112-
For detailed usage instructions and test server notes, please refer to 👉 [XiaoZhi Test Server Help Guide](https://xiaozhi.me/help).
124+
For server deployment on personal computers, refer to another MIT-licensed project [xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server)
113125

114126
## Star History
115127

0 commit comments

Comments
 (0)