openai-whisper

Install command: 
brew install openai-whisper

General-purpose speech recognition model

https://github.com/openai/whisper

License: MIT

Development: Pull requests

Formula JSON API: /api/formula/openai-whisper.json

Formula code: openai-whisper.rb on GitHub

Bottle (binary package) installation support provided for:

macOS on
Apple Silicon		 golden gate ✅
tahoe ✅
sequoia ✅
sonoma ✅
macOS on
Intel		 sonoma ✅
Linux ARM64 ✅
x86_64 ✅

Current versions:

stable ✅ 20250625
head ⚡️ HEAD

Revision: 6

Depends on:

certifi 2026.7.22 Mozilla CA bundle for Python
ffmpeg 9.0.2 Play, record, convert, and stream select audio and video codecs
llvm@22 22.1.8 Next-gen compiler infrastructure
python@3.14 3.14.8 Interpreted, interactive, object-oriented programming language
pytorch 2.14.0 Tensors and dynamic neural networks

Depends on when building from source:

cmake 4.4.3 Cross-platform make
pkgconf 3.0.7 Package compiler and linker metadata toolkit
rust 1.98.1 Safe, concurrent, practical language

Binaries: whisper

Known vulnerabilities in the current version:

GHSA-8988-9cw3-xx77 urllib3: HTTPS proxy TLS configuration may be ignored or overridden
GHSA-vxq7-64xx-v4gw urllib3: HTTPResponse.stream()/read_chunked() buffers an unbounded chunk-size line into memory

Data from Homebrew/advisory-database. Run brew vulns openai-whisper for a live check.

Analytics:

30 days90 days365 days
Installs1,23310,103111,022
Installs (--HEAD)08141
Installs on Request1,23110,098111,011
Installs on Request (--HEAD)08141
Build Errors0