MLX-Audio runs audio models with Apple's MLX: text-to-speech, speech-to-text, speech-to-speech and more. It comes as a Python package with a command line, and there's a Swift package for iOS and macOS apps.
It's made for Apple silicon Macs and needs MLX, which runs on macOS 14.0 or later. Some voices need extra packages (Kokoro needs misaki).
It's free and open source (MIT) and runs on your Mac.
Official downloads only. MLX never re-hosts an app, and never runs a command for you.
Ranked against the developer tools listings, from real public data only. How the score works.
MLX-Audio is a product of Prince Canuma; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.