Verified project record

moeru-ai/airi

A self-hosted AI VTuber companion application that handles realtime voice chat and game interaction, running on desktop and browser platforms with optional native GPU acceleration and multiple optional external LLM and TTS provider integrations.

Project overview

Project type: AI Agent · Audio & Speech
Use cases: Automation
Deployment: Refer to project documentation
License: MIT

Best for

Creators and general users who want a self-hosted VTuber application that they own and can run locally or in a browser.
Users who require multi-platform chat integration via Discord or Telegram with flexible, optional external TTS and LLM services.
Users seeking native GPU acceleration via NVIDIA CUDA or Apple Metal on the desktop application can use these features.

Key capabilities

Supports ElevenLabs, Microsoft/Azure Speech, OpenAI-compatible TTS, Alibaba Cloud Model Studio, and local Kokoro TTS.
Allows loading, controlling, and animating VRM and Live2D models with auto blink, look at, and idle eye movements.
Enables direct chatting within Telegram and Discord platforms.
Provides pure in-browser database support using DuckDB WASM or pglite.
Desktop version uses native NVIDIA CUDA and Apple Metal, while the browser version uses WebGPU.
Plans to support running inference locally inside the browser using WebGPU.

Limitations and risks

The project is in the early stages of development and is currently seeking talented developers to help build the application.
Adopters should be aware of the risk associated with the project being in an early stage of development.

Getting started

Desktop binaries and a hosted web version are available without code compilation. Users can start by downloading an installer or opening the hosted demo.

Evidence and sources

GitHub project description: 💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime…
README: Re-creating Neuro-sama, a soul container of AI waifu / virtual characters to bring them into our world.
README: Unlike the other AI driven VTuber open source projects, アイリ was built with support of many Web technologies such as [WebGPU](https://www.w3.org/TR/webgpu/), [WebAudio](https://dev…
README: We are still in the early stage of development where we are seeking out talented developers to join us and help us to make アイリ a reality.
README: - [x] Multi-provider voice synthesis, including [ElevenLabs](https://elevenlabs.io/), Microsoft/Azure Speech, OpenAI-compatible TTS, Alibaba Cloud Model Studio, and local Kokoro T…

Reviewed at: 2026-07-17T09:03:42Z