Skip to content
@FluidInference

Fluid Inference

intelligence everywhere
README.md

👋

We are building small, personalized models. Everything is open sourced.

Conversion scripts are opensourced in mobius.

Join our Discord or check out our models on Hugging Face:

Discord Hugging Face Models

Read our blogs here

Pinned Loading

  1. FluidAudio FluidAudio Public

    Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

    Swift 2.9k 432

  2. FluidUse FluidUse Public

    Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API

    Swift 152 12

  3. mobius mobius Public

    Your models on any xPU

    Python 94 25

  4. swift-scribe swift-scribe Public

    Fully local, no dependency scribe. Speak into your microphone and summarize. Requires iOS 26 and MacOS 26 to use the advanced transcription model and foundational model for summaries

    Swift 316 41

  5. text-processing-rs text-processing-rs Public

    Rust port of NVIDIA NeMo Text Processing for Inverse Text Normalization

    Rust 47 16

  6. fluidaudio-rs fluidaudio-rs Public

    Rust 22 14

Repositories

Showing 10 of 20 repositories
  • FluidAudio Public

    Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

    FluidInference/FluidAudio's past year of commit activity
    Swift 2,876 Apache-2.0 432 12 10 Updated Sep 24, 2026
  • FluidUse Public

    Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API

    FluidInference/FluidUse's past year of commit activity
    Swift 152 Apache-2.0 12 0 4 Updated Sep 24, 2026
  • mobius Public

    Your models on any xPU

    FluidInference/mobius's past year of commit activity
    Python 94 Apache-2.0 25 1 10 Updated Sep 24, 2026
  • text-processing-rs Public

    Rust port of NVIDIA NeMo Text Processing for Inverse Text Normalization

    FluidInference/text-processing-rs's past year of commit activity
    Rust 47 Apache-2.0 16 0 2 Updated Sep 24, 2026
  • fluidaudio-web Public

    In-browser inference for FluidAudio's core models (ASR/TTS/diarization) via WebGPU + WebAssembly — no server

    FluidInference/fluidaudio-web's past year of commit activity
    TypeScript 8 MIT 1 0 0 Updated Sep 15, 2026
  • .github Public
    FluidInference/.github's past year of commit activity
    0 0 0 0 Updated Sep 10, 2026
  • fluidaudio-rs Public
    FluidInference/fluidaudio-rs's past year of commit activity
    Rust 22 14 0 2 Updated Jul 23, 2026
  • eddy-audio Public

    In fluid dynamics, an eddy is the swirling of a fluid and the reverse current created when the fluid is in a turbulent flow regime.

    FluidInference/eddy-audio's past year of commit activity
    C++ 19 Apache-2.0 2 1 0 Updated Jul 23, 2026
  • FluidVad Public

    Lightweight Silero VAD v6 for electron apps

    FluidInference/FluidVad's past year of commit activity
    Rust 2 MIT 0 0 0 Updated Jul 21, 2026
  • swift-scribe Public

    Fully local, no dependency scribe. Speak into your microphone and summarize. Requires iOS 26 and MacOS 26 to use the advanced transcription model and foundational model for summaries

    FluidInference/swift-scribe's past year of commit activity
    Swift 316 MIT 41 0 0 Updated Jul 10, 2026
View all repositories