Your friendly personal AI
Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.
Open and extensible. Built for you.
We support people like you who play by their own rules. Easily integrate with your favorite tools and services to make Amica work for you. Self host or use cloud services. The choice is yours.
Now is the time to build your friend.
With typical apps, you have to enter your personal information and hope that they don’t sell it to the highest bidder. With Amica, you don’t have to worry about that. We don’t even know who you are.
Empower your AI
We are building the tools to help you build the best AI possible.
Use any model
Try out any model you want, we support almost all. Even the really bad ones.
Communicate in real-time
Our goal is to make sure you have the best experience possible.
Implement new features
We are constantly looking for skilled developers to help us build new features.
Private and anonymous
When running with local models nothing is sent to the cloud, your data always remains yours.
Educational
Learn any subject with the help of a friend. Suitable for all ages, even really old.
Frequently asked questions
If you have anything else you want to ask, reach out to us.
I don't have any experience with AI, can I still use Amica?
Yes, we are building Amica to be as easy to use as possible. We want to make AI accessible to everyone.
How do I get started?
Download or open the app, set it up with your API details, and start chatting with your AI friend.
What is an AI friend?
An AI friend is an AI that you can talk to. It can be anything you want, a person, a character, or even a pet.
How do I contribute?
We are always looking for skilled developers to help us build new features. Try looking for issues on our GitHub page.
But I'm not a developer!?
Our parent company is building a decentralized AI platform and associated cryptocurrency token. You could buy that to help fund Amica development. Or just share the project if you find it useful.
Can I fork Amica?
Of course. The software license is MIT. We would love to see what you build. Please contribute back to the project if you can. This project started as a fork of pixiv/ChatVRM.
What model does Amica use?
The public demo uses OpenChat 3.5 by Alignment Lab, which is based on Mistral 7B.
What about the voice?
The demo uses XTTSv2 by Coqui AI, with a voice that comes from a member of our team.
How about transcription?
The demo uses Whisper Tiny by OpenAI. This runs very fast, but is not as accurate as other models. With local setup, you may want to use a larger model.