#151 · Primary category: AI Chatbots

amica

ai assistant-chat-bots computer-vision llm speech-recognition tts

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

Project last updated:07/23/25

GitHub Stars

1.6K

Forks

268

Contributors

21

License

MIT

Why we included this project

Amica is a browser-based chat interface that pairs an LLM backend with a customizable 3D avatar, and it handles the full voice loop. It accepts speech through Whisper and Silero VAD, returns spoken replies through any of the supported TTS engines, and renders VRM characters you can import and adjust. The chat layer stays backend-agnostic: you can point it at local llama.cpp or Ollama, or at any OpenAI-compatible API, which makes prototyping without vendor lock-in straightforward. Because it began as a fork of Pixiv's ChatVRM, the code is approachable and documented, and you can run it as a web app or a Tauri desktop build. Teams building a lively talking avatar rather than a plain text assistant will find it a practical reference.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category