We're an applied AI research lab building small, personalized models. If we derive from an open-source model, it stays open source.
Conversion scripts are opensourced in mobius.
Join our Discord or check out our models on Hugging Face:
Read our blogs here
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.
In-browser inference for FluidAudio's core models (ASR/TTS/diarization) via WebGPU + WebAssembly — no server
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.
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
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
