Skip to content

blixor7/Ai-avatar-chatbot

Repository files navigation

Virtual AI Assistant

A fully open-source AI powered virtual companion that combines chatbot intelligence, voice interaction, and visual avatar movement. Designed to run locally with minimal GPU requirements.


Project Objective

To build a lightweight AI chatbot with a virtual avatar that:

  • Runs on your local machine
  • Requires minimal hardware resources
  • Supports multiple AI backends (local or online)
  • Provides both chat and voice-based interaction

Installation Video Guides


Installation Steps

  1. Install ffmpeg on your system.
  2. Install VTube Studio.
  3. Download the latest release .zip.
  4. Extract the archive and rename Example env.txt.env.
  5. Launch VTube Studio and enable API Access from settings.
  6. Run start.bat.
  7. Grant the plugin permission in VTube Studio.
  8. Use CTRL + Mic in the terminal to activate speech input.

Features

  • Integration with Oobabooga
  • Support for Character.ai (beta)
  • Local or cloud-based LLMs (via Colab or on-device)
  • Real-time avatar interaction with speech & chat

System Requirements


Troubleshooting


Documentation


Roadmap

  • Voicevox integration
  • Oobabooga text generation
  • Local & Colab LLM inference
  • Local-only execution without Character.AI
  • Internet-enabled assistant
  • Continuous improvements planned

Contributing

We welcome community contributions!

  • Report bugs via Issues
  • Submit pull requests for fixes & improvements
  • Propose new features in the discussion board

Support

If you find this project useful, consider supporting via PayPal.


Credits & References

This project builds upon the work of many open-source initiatives:

Special thanks to Alexander Lewis for community contributions.


License

Licensed under MIT. Copyright © 2023


Clean. Modular. Open-source. Your AI Avatar Companion.

About

A fully open-source AI powered virtual companion that combines chatbot intelligence, voice interaction, and visual avatar movement. Designed to run locally with minimal GPU requirements.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors