Milo is a framework for incorporating a voice conversation agent, that uses LLM models for natural speech conversation. The framework along with a setup guid, can be read from link to toturial PPT
- recieve RTP audio transcribe and response
- suport for GPT-3 \ 4 \ chat models
- suport for custom models from huggingface
- unity SDK for XRInteractionToolkit
For detailed instruction of how to install Milo, you can follow this link to toturial PPT
- Clone the repository:
git clone https://github.com/Advanced-Reality-Lab/Milo.git
- Navigate to the project directory:
cd Milo - Install dependencies:
pip install -r requirements.txt
- Add the Milo SDK to unity from Unity Package
A Unity demo project for the use of Milo SDK is avilable at UnityDemo or from the package provided Unity Package
We wellcome any conributions, following these guidelines:
- contributions needs to have a pull request with a description of the add \ fix.
- contribution needs to be reviewed before adding into the main branch
- Bug reports are wellcome, using issues, and even more wellcome with a pull request. 🚀
This project is licensed under the Academic Free License v3.0 - see the LICENSE file for details.
If you use this project in your research, please cite it as follows:
@ARTICLE{10.3389/frvir.2025.1555173,
AUTHOR={Shoa, Alon and Friedman, Doron },
TITLE={Milo: an LLM-based virtual human open-source platform for extended reality},
JOURNAL={Frontiers in Virtual Reality},
VOLUME={Volume 6 - 2025},
YEAR={2025},
URL={https://www.frontiersin.org/journals/virtual-reality/articles/10.3389/frvir.2025.1555173},
DOI={10.3389/frvir.2025.1555173},
ISSN={2673-4192},
}