whisper.cpp

Install command:
brew install whisper.cpp

Formerly known as: whisper-cpp

Port of OpenAI's Whisper model in C/C++

https://github.com/ggml-org/whisper.cpp

License: MIT

Development: Pull requests

Formula JSON API: /api/formula/whisper.cpp.json

Formula code: whisper.cpp.rb on GitHub

Bottle (binary package) installation support provided for:

macOS on
Apple Silicon
tahoe
sequoia
Linux ARM64
x86_64

Current versions:

stable 1.9.4
head ⚡️ HEAD

Depends on:

ggml 0.23.0 Tensor library for machine learning
llama.cpp 0.4.0 LLM inference in C/C++
sdl2-compat 2.32.72 SDL2 compatibility layer that uses SDL3 behind the scenes

Depends on when building from source:

cmake 4.4.3 Cross-platform make

Binaries: parakeet-cli, parakeet-quantize, whisper-bench, whisper-cli, whisper-command, whisper-lsp, whisper-quantize, whisper-server, whisper-stream, whisper-talk-llama, whisper-vad-speech-segments

whisper.cpp requires GGML model files to work. These are not downloaded by default.
To obtain model files (.bin), visit one of these locations:

    https://huggingface.co/ggerganov/whisper.cpp/tree/main
    https://ggml.ggerganov.com/

Analytics:

30 days90 days365 days
Installs666
Installs on Request666
Build Errors0