Fluid Inference

FluidAudio

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-scribe

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-parakeet-mlx

Based on senstella/parakeet-mlx

mobius

Your models on any xPU

Fluid.OpenVINO.GenAI

OpenVINO and OpenVINO GenAI, Interop in .NET for GenAI workloads

fluidtop

MacOS hardware performance monitoring CLI tool with a focus on AI Workloads

fluid-server

Local AI server for your Windows apps.

.github

openvino.genai

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime