# Install whisper-cpp with Homebrew, apk, dnf, Nix, scoop Port of OpenAI's Whisper model in C/C++. Version 1.9.1 via Homebrew; verified 2026-06-19. ## Install ```sh sudo av install brew:whisper-cpp ``` Additional install commands: ### macOS - Homebrew (100%): ```sh brew install whisper-cpp ``` Evidence: local Homebrew formula metadata ### Linux - apk (92%): ```sh sudo apk add whisper-server ``` Evidence: Alpine Linux edge package indexes: whisper-server from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz - dnf (92%): ```sh sudo dnf install whisper-cpp ``` Evidence: Fedora Rawhide package metadata: whisper-cpp from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst - Nix (92%): ```sh nix profile install nixpkgs#whisper-cpp ``` Evidence: nixpkgs package indexes: pkgs/by-name/wh/whisper-cpp/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1 ### Windows - Scoop (92%): ```sh scoop install main/whisper-cpp ``` Evidence: Scoop official bucket manifest trees: bucket/whisper-cpp.json from https://api.github.com/repos/ScoopInstaller/Main/git/trees/master?recursive=1 ## Package facts - **Package key:** brew:whisper-cpp - **Package manager:** Homebrew - **Package manager page:** - **Version:** 1.9.1 - **Source summary:** Port of OpenAI's Whisper model in C/C++ - **Homepage:** - **Repository:** - **Upstream docs:** - **License:** MIT - **Source archive:** - **Last updated:** 2026-06-19T09:02:25Z - **Generated:** 2026-07-08T07:18:31+00:00 ## Executables - whisper-bench (cli) - whisper-cli (cli) - whisper-command (cli) - whisper-lsp (cli) - whisper-quantize (cli) - whisper-server (cli) - whisper-stream (cli) - whisper-talk-llama (cli) - whisper-vad-speech-segments (cli) - whisper-bench (alias) - whisper-cli (alias) - whisper-command (alias) - whisper-lsp (alias) - whisper-quantize (alias) - whisper-server (alias) - whisper-stream (alias) - whisper-talk-llama (alias) - whisper-vad-speech-segments (alias) ## Dependencies - ggml - sdl2-compat ## Build dependencies - cmake ## Install behavior - Post-install hook: not defined - Caveats: 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/ - Bottle: available on arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux ## Freshness - Page generated: 2026-07-08 - Package-manager version: 1.9.1 - Package-manager updated: 2026-06-19 - Local data: ok - Upstream repository: https://github.com/ggml-org/whisper.cpp - Upstream latest detected: v1.9.1 (current) ## Project history and usage whisper.cpp is Georgi Gerganov's C and C++ runtime for OpenAI's Whisper speech-recognition models. It appeared days after OpenAI released Whisper in September 2022 and turned the Python/PyTorch reference implementation into a small, portable, dependency-light local transcription tool. ### Project history OpenAI introduced Whisper on September 21, 2022 as an automatic speech recognition system trained on 680,000 hours of multilingual and multitask supervised data. The original OpenAI repository positioned Whisper as a general-purpose model for multilingual transcription, translation to English, and language identification. The whisper.cpp repository was created on September 25, 2022. Its README describes the project as a port of OpenAI's Whisper model in C/C++, with the high-level model implementation contained in `whisper.h` and `whisper.cpp` and the lower-level tensor work handled by ggml. That made Whisper usable in environments where Python, PyTorch, or CUDA were undesirable or unavailable. The project grew with ggml-style model conversion, quantization, platform backends, examples, bindings, and command-line tools. Its model documentation explains that original OpenAI PyTorch models are converted to ggml format for loading from C/C++, while project discussions and release notes document features such as integer quantization, streaming, server usage, and embedded-device experiments. ### Adoption history whisper.cpp became one of the canonical local-AI command-line packages because it made a large neural speech model feel like a normal Unix tool: download a converted model, run an executable, and transcribe local audio without a cloud service. The upstream GitHub repository reported more than 51,000 stars and more than 5,700 forks via GitHub's API on July 2, 2026. Its adoption also matters historically because it helped establish the ggml pattern later associated with local inference projects: compact C/C++ runtimes, quantized model files, CPU-first portability, and optional acceleration paths. In package-manager culture, whisper.cpp is the package people reach for when they want OpenAI Whisper behavior in scripts, media pipelines, offline transcription jobs, and low-power devices. ### How it is used Typical usage is local speech-to-text: converting or downloading a ggml-format Whisper model, running `whisper-cli` or related tools against audio, and emitting transcripts or timestamps. The repository also ships examples and executables for benchmarking, streaming microphone input, running a local server, quantizing models, and integrating with other applications through a C API or bindings. The package is especially useful when privacy, offline operation, repeatable batch processing, or hardware portability matter more than managed cloud transcription. Users choose model size and quantization level as the tradeoff knob between accuracy, memory footprint, and speed. ### Why package nerds care For package nerds, whisper.cpp is a landmark local-inference package: it compressed a research model into a buildable C/C++ artifact that could live comfortably in Homebrew, Linux distributions, Docker images, mobile apps, WebAssembly experiments, and single-purpose transcription workflows. It also became a reference point for later local-AI ports. When people compare local speech runtimes, they often distinguish broad cross-platform portability in whisper.cpp from Apple-specific Core ML and Neural Engine approaches such as WhisperKit, or Python/GPU-oriented projects such as faster-whisper. ### Timeline - 2022-09-21: OpenAI introduced Whisper and released model code and weights for multilingual speech recognition. - 2022-09-25: The whisper.cpp GitHub repository was created. - 2023: whisper.cpp discussions and releases documented integer quantization, streaming, and embedded-device experiments. - 2026-07-02: GitHub API metadata showed the repository above 51,000 stars, reflecting broad adoption in the local-AI ecosystem. ### Related projects - OpenAI Whisper is the upstream model and Python reference implementation. - ggml is the low-level machine-learning library and model-format ecosystem used by whisper.cpp. - WhisperKit targets Apple Silicon with Swift and Core ML rather than whisper.cpp's cross-platform C/C++ approach. ### Sources - OpenAI Whisper announcement: https://openai.com/index/whisper/ - OpenAI Whisper repository: https://github.com/openai/whisper - whisper.cpp GitHub API metadata: https://api.github.com/repos/ggml-org/whisper.cpp - whisper.cpp model documentation: https://github.com/ggml-org/whisper.cpp/blob/master/models/README.md - whisper.cpp repository and README: https://github.com/ggml-org/whisper.cpp - whisper.cpp v1.4.0 quantization discussion: https://github.com/ggml-org/whisper.cpp/discussions/838 ## Security Notes broad file, network, media, or database tool signal. - **Geiger risk:** blue / medium - broad file, network, media, or database tool signal ## Source Database Details - **Source Database:** Homebrew formula API - **Tap:** homebrew/core - **Full Name:** whisper-cpp - **Version Scheme:** 0 - **Revision:** 0 - **Head Version:** HEAD - **Bottle Stable Root URL:** - **Deprecated:** no - **Disabled:** no - **Keg Only:** no - **URL Keys:** head, stable ## Other Package-Manager Records - Nix - whisper-cpp: normalized package name match | nixpkgs package indexes: pkgs/by-name/wh/whisper-cpp/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1 - apk - whisper-server - 1.8.4-r2: normalized package name match | Alpine Linux edge package indexes: whisper-server from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz | whisper.cpp server | https://github.com/ggerganov/whisper.cpp - apk - whisper-server-openrc - 1.8.4-r2: normalized package name match | Alpine Linux edge package indexes: whisper-server-openrc from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz | whisper.cpp server (OpenRC init scripts) | https://github.com/ggerganov/whisper.cpp - apk - whisper.cpp - 1.8.4-r2: normalized package name match | Alpine Linux edge package indexes: whisper.cpp from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz | Port of OpenAI's Whisper model in C/C++ | https://github.com/ggerganov/whisper.cpp - apk - whisper.cpp-dev - 1.8.4-r2: normalized package name match | Alpine Linux edge package indexes: whisper.cpp-dev from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz | Port of OpenAI's Whisper model in C/C++ (development files) | https://github.com/ggerganov/whisper.cpp - apk - whisper.cpp-libs - 1.8.4-r2: normalized package name match | Alpine Linux edge package indexes: whisper.cpp-libs from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz | Port of OpenAI's Whisper model in C/C++ | https://github.com/ggerganov/whisper.cpp - apk - whisper.cpp-vulkan - 1.8.4-r2: normalized package name match | Alpine Linux edge package indexes: whisper.cpp-vulkan from https://dl-cdn.alpinelinux.org/alpine/edge/testing/x86_64/APKINDEX.tar.gz | Port of OpenAI's Whisper model in C/C++ (Vulkan backend) | https://github.com/ggerganov/whisper.cpp - dnf - whisper-cpp - 1.8.3-1.fc45: normalized package name match | Fedora Rawhide package metadata: whisper-cpp from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | Port of OpenAI's Whisper model in C/C++ | https://github.com/ggerganov/whisper.cpp - dnf - whisper-cpp-devel - 1.8.3-1.fc45: normalized package name match | Fedora Rawhide package metadata: whisper-cpp-devel from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | Libraries and headers for whisper-cpp | https://github.com/ggerganov/whisper.cpp - Scoop - main/whisper-cpp: normalized package name match | Scoop official bucket manifest trees: bucket/whisper-cpp.json from https://api.github.com/repos/ScoopInstaller/Main/git/trees/master?recursive=1 ## Related links - [Source-control packages](https://www.automicvault.com/pkg/source-control-tools/) - Belongs to a source-control command family. - [Secret-risk packages](https://www.automicvault.com/pkg/secret-risk-packages/) - Has protected-tool coverage, approval-gate, or non-low Geiger security signals. - [Terminal utility packages](https://www.automicvault.com/pkg/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [Text processing packages](https://www.automicvault.com/pkg/text-processing-tools/) - Matched text, document, or structured-data processing metadata. - [sdl2-compat](https://www.automicvault.com/pkg/brew/sdl2-compat/) - Runtime dependency declared by Homebrew. - [cmake](https://www.automicvault.com/pkg/brew/cmake/) - Build dependency declared by Homebrew. - [auto-editor](https://www.automicvault.com/pkg/brew/auto-editor/) - Popular package that depends on this formula. - [ffmpeg-full](https://www.automicvault.com/pkg/brew/ffmpeg-full/) - Popular package that depends on this formula. - [whisperkit-cli](https://www.automicvault.com/pkg/brew/whisperkit-cli/) - Shares av.db curated category or tags: cli, media, speech-recognition, speech-to-text, whisper. - [openai-whisper](https://www.automicvault.com/pkg/brew/openai-whisper/) - Shares av.db curated category or tags: cli, machine-learning, media, speech-recognition. - [cmu-pocketsphinx](https://www.automicvault.com/pkg/brew/cmu-pocketsphinx/) - Shares av.db curated category or tags: cli, media, speech-recognition. - [cmuclmtk](https://www.automicvault.com/pkg/brew/cmuclmtk/) - Shares av.db curated category or tags: cli, media, speech-recognition. - [julius](https://www.automicvault.com/pkg/brew/julius/) - Shares av.db curated category or tags: cli, media, speech-recognition. - [blitzwave](https://www.automicvault.com/pkg/brew/blitzwave/) - Shares av.db curated category or tags: c, cli, media. - [codec2](https://www.automicvault.com/pkg/brew/codec2/) - Shares av.db curated category or tags: c, cli, media. - [ebook-tools](https://www.automicvault.com/pkg/brew/ebook-tools/) - Shares av.db curated category or tags: c, cli, media. - [pocket-tts](https://www.automicvault.com/pkg/brew/pocket-tts/) - Local package facts share a topical domain. Shared terms: cli, learning, machine, machine-learning, media. ## Combined YAML source View the package source record on GitHub. [combined/whisper-cpp.yml](https://github.com/automic-vault/db/blob/main/combined/whisper-cpp.yml) ## Sources - Nucleus package database - Geiger risk classifier - package-page enrichment - curated package history - package version freshness - av.db category and tag curation - package relationship graph - external package-manager database matches - cross-ecosystem install command graph