Xybrid
A cross-platform toolkit for running language models, speech recognition and text-to-speech natively inside apps and games, on Flutter, Swift, Kotlin, Unity or Rust, entirely offline.
Xybrid is a toolkit for running large language models, automatic speech recognition and text-to-speech natively on-device, across Flutter, Swift, Kotlin, Unity and Rust. It targets apps and games that need private, offline AI without a cloud dependency.
It packages the runtime and bindings needed to embed local models directly into a mobile app, desktop app or game engine, so inference, voice input and voice output happen on the user's own hardware rather than a remote server.
The project is written in Rust and distributed as packages for crates.io, pub.dev, Maven Central and the Swift Package Manager, and is released under the Apache 2.0 license.