FluidAudio

![banner.png](banner.png)

# FluidAudio - Transcription, Text-to-speech, VAD, Speaker diarization with CoreML Models

[![Swift](https://img.shields.io/badge/Swift-6.0+-orange.svg)](https://swift.org)
[![Platform](https://img.shields.io/badge/Platform-macOS%20%7C%20iOS-blue.svg)](https://developer.apple.com)
[![Documentation](https://img.shields.io/badge/Documentation-docs.fluidinference.com-008574.svg)](https://docs.fluidinference.com/introduction)
[![Discord](https://img.shields.io/badge/Discord-Join%20Chat-7289da.svg)](https://discord.gg/WNsvaCtmDe)
[![Hugging Face Models](https://img.shields.io/badge/Hugging%20Face%20Models-500k%2B%20Monthly%20Downloads-brightgreen?logo=huggingface)](https://huggingface.co/FluidInference)


<div align="center">

<a href="https://trendshift.io/repositories/26004?utm_source=repository-badge&amp;utm_medium=badge&amp;utm_campaign=badge-repository-26004" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/26004" alt="FluidInference%2FFluidAudio | Trendshift" width="250" height="55"/></a>

</div>


FluidAudio is a Swift SDK for fully local, low-latency audio AI on Apple devices, with inference offloaded to the Apple Neural Engine (ANE), resulting in less memory and generally faster inference.

The SDK includes state-of-the-art speaker diarization, transcription, and voice activity detection via open-source models (MIT/Apache 2.0) that can be integrated with just a few lines of code. Models are optimized for background processing, ambient computing and always on workloads by running inference on the ANE, minimizing CPU usage and avoiding GPU/MPS entirely.

For custom use cases, feedback, additional model support, or platform requests, join our [Discord](https://discord.gg/WNsvaCtmDe). We're also bringing visual, language, and TTS models to device and will share updates there.

Below are some featured local AI apps using Fluid Audio models on macOS and iOS:

<p align="left">
  <a href="https://github.com/Beingpax/VoiceInk/"><img src="Documentation/assets/voiceink.png" height="40" alt="Voice Ink"></a>
  <a href="https://altic.dev/fluid"><img src="Documentation/assets/fluidvoice.png" height="40" alt="Fluid Voice"></a>
  <a href="https://github.com/anomalyco/hex"><img src="Documentation/assets/hex.png" height="40" alt="Hex"></a>
  <a href="https://spokenly.app/"><img src="Documentation/assets/spokenly.png" height="40" alt="Spokenly"></a>
  <a href="https://boltai.com/"><img src="Documentation/assets/boltai.png" height="40" alt="BoltAI"></a>
  <a href="https://paraspeech.com"><img src="Documentation/assets/paraspeech.png" height="40" alt="Paraspeech"></a>
  <a href="https://snaply.ai"><img src="Documentation/assets/snaply.png" height="40" alt="Snaply"></a>
  <a href="https://github.com/yazinsai/OpenOats"><img src="Documentation/assets/openoats.png" height="40" alt="OpenOats"></a>
  <a href="https://talat.app"><img src="Documentation/assets/talat.png" height="40" alt="Talat"></a