{
  "slug": "whisper-cpp",
  "name": "whisper.cpp",
  "category": "Multimodal / Speech",
  "tagline": "Local speech-to-text with Metal GPU acceleration and optional Core ML on Apple silicon.",
  "kit_says": "Ears for a local agent. On Apple silicon the README says inference runs fully on the GPU via Metal.",
  "homepage": "https://github.com/ggml-org/whisper.cpp",
  "repo": "https://github.com/ggml-org/whisper.cpp",
  "docs": "https://github.com/ggml-org/whisper.cpp#readme",
  "license": "MIT",
  "platforms": [
    "macos-apple-silicon",
    "linux",
    "windows"
  ],
  "mac_studio_fit": "Primary",
  "what_it_is": "A C/C++ port of OpenAI's Whisper speech recognition model. Builds with CMake; ships whisper-cli and model download scripts.",
  "gap_role": "Voice input: private, offline transcription that pairs with local LLMs.",
  "prerequisites": [
    "Xcode Command Line Tools (xcode-select --install)",
    "CMake (brew install cmake)",
    "git"
  ],
  "install": {
    "macos-apple-silicon": [
      {
        "run": "xcode-select --install   # skip if already installed"
      },
      {
        "run": "brew install cmake"
      },
      {
        "run": "git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp"
      },
      {
        "run": "sh ./models/download-ggml-model.sh base.en"
      },
      {
        "run": "cmake -B build && cmake --build build -j --config Release"
      }
    ],
    "linux": [
      {
        "run": "git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp && sh ./models/download-ggml-model.sh base.en && cmake -B build && cmake --build build -j --config Release"
      }
    ]
  },
  "configure": [
    {
      "run": "# optional: Core ML encoder on the Apple Neural Engine; see the README's 'Core ML support' section"
    }
  ],
  "verify": [
    {
      "run": "./build/bin/whisper-cli -f samples/jfk.wav",
      "expect": "prints a transcript of the bundled JFK sample"
    }
  ],
  "rollback": [
    {
      "run": "cd .. && rm -rf whisper.cpp",
      "note": "removes source, build and downloaded models"
    }
  ],
  "caveats": [
    "whisper-cli currently only accepts 16-bit WAV input; convert other formats first (README)."
  ],
  "works_with": [
    "ollama",
    "open-webui"
  ],
  "sources": [
    "https://github.com/ggml-org/whisper.cpp"
  ],
  "sponsored": false,
  "verified_on": "2026-10-15",
  "gap_score": {
    "value": null,
    "status": "pending test on Mac Studio",
    "baseline": "frontier reference (see /about#gap-score)"
  },
  "benchmarks": {
    "status": "pending test on Mac Studio",
    "rig": "Mac Studio, Apple Silicon, 128GB unified memory",
    "results": []
  },
  "hardware_tested": [],
  "repo_meta": {
    "stars": 54413,
    "stars_as_of": "2026-10-15",
    "last_push": "2026-10-12",
    "archived": false,
    "license_spdx": "MIT"
  },
  "stack_layer": "tools",
  "summary": {
    "what": "Speech-to-text that runs on your machine.",
    "why": "Talk to your agent, offline and private."
  }
}