whisper.cpp transcribes speech to text with OpenAI's Whisper models. It is a plain C/C++ program with a command-line tool, whisper-cli, and a library other apps build on.
Apple silicon is a first-class target: inference runs on the GPU through Metal, and the encoder can run on the Neural Engine through Core ML. The project recommends macOS 14 (Sonoma) or newer for Core ML.
It is free and open source (MIT) and runs entirely on your Mac. Install it with Homebrew (brew install whisper.cpp).
brew install whisper.cppOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
Ranked against the voice & audio listings, from real public data only. How the score works.
whisper.cpp is a product of ggml-org; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.