Skip to content

A library for ESP32 access to the large model platform to realize voice dialogue, supporting ESP32-S3 and ESP32-P4

License

Notifications You must be signed in to change notification settings

waveshareteam/ESP32-AIChats

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 

Repository files navigation

Waveshare ESP32 AIChats ProJects

Welcome to the Waveshare ESP32-AIChats repository! This project aims to share a solution for connecting the ESP32 to cloud-based large models, enabling voice interaction and conversational AI. The purpose of this repository is to provide resources and insights related to ESP32-based voice interfaces, integrating with powerful cloud models to offer real-time communication and AI capabilities.

Whether you are looking to explore voice recognition, cloud AI integration, or build your own conversational systems using the ESP32, this repository provides the necessary tools, tutorials, and example code to help you get started. Join us on this exciting journey of learning and developing innovative AI-driven voice solutions!

Feel free to explore, contribute, and share your ideas with the community. We hope this repository helps you develop your own ESP32 voice-enabled applications and enhances your understanding of large-scale AI models.

Happy coding!


📦 Repository Contents

1. Openai(Updated soon)

Multimodal conversational AIGC coming soon... RTC transmission technology can provide a more natural and efficient interactive experience for applications

2. Doubao(Updated soon)

doubao expands multimodal low-latency interaction, currently in beta, and will be launched in the future

3. Others

  • xiaozhi : helps build an AI chatbot using the ESP32-S3 board. It features voice recognition, text-to-speech, and multi-language support, enabling users to create their own AI assistant with offline capabilities.

📚 Documentation

Documentation will be rolled out with different models


🚀 Getting Started

Prerequisites

  • Hardware:
  • Software:
    • ESP-IDF(Each product has a recommended version on the wiki as well as sample routines)

🌟 Features

  • LVGL Support:
    • Widgets, animations, and custom UI components for Waveshare displays.
  • With touch function:
    • Combined with LVGL, use touch to trigger dialogue, etc
  • Arduino-Compatible Libraries:
    • Easy porting of code using the Arduino ecosystem.

🔧 Configuration

You can view some of the configurations that have been added via menuconfig, which will allow you to verify the functionality directly


📂 Directory Structure

.
├── openai/           # openai large model
├── doubao/           # doubao large model
├── others/           # Other Solutions
└── README.md         # Project overview (this file)

🛠️ Contributing

We welcome contributions! Here’s how you can help:

  1. Fork the repository.
  2. Create a new branch for your feature or bug fix.
  3. Commit your changes with clear descriptions.
  4. Submit a pull request for review.

🧩 Issues and Support

If you encounter any issues:

  • Check the Issues section.
  • Create a new issue with detailed information.
  • Refer to the documentation for troubleshooting tips.

📜 License

This repository is licensed under the Apache License. See the LICENSE file for details.


🙌 Acknowledgments

  • Waveshare for their excellent hardware platforms and software support
  • The Espressif Team for their continuous support.
  • 虾哥的xiaozhi-ESP32 Low code amount of open source projects Support
  • openai-realtime-embedded-sdk SDK Low-level Support
  • Open-source contributors who make these projects possible.

Thank you for using Waveshare ESP32-AIChats! 🚀

About

A library for ESP32 access to the large model platform to realize voice dialogue, supporting ESP32-S3 and ESP32-P4

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages