whisper-cpp

{
  "aliases": [],
  "alternatives": [
    "openai-whisper",
    "faster-whisper",
    "whisper.js"
  ],
  "build_dependencies": [
    "cmake"
  ],
  "categories": [
    "inference",
    "speech-recognition",
    "ml",
    "library"
  ],
  "caveats": "whisper-cpp requires GGML model files to work. These are not downloaded by default.\nTo obtain model files (.bin), visit one of these locations:\n\n  https://huggingface.co/ggerganov/whisper.cpp/tree/main\n  https://ggml.ggerganov.com/\n",
  "conflicts_with": [],
  "dependencies": [
    "ggml",
    "sdl2-compat"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Port of OpenAI\u0027s Whisper model in C/C++",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:40:45+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "whisper-cpp",
  "github_default_branch": "master",
  "github_last_commit_at": "2026-06-19T09:53:47Z",
  "github_readme_excerpt": "# whisper.cpp\n\n![whisper.cpp](https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg)\n\n[![Actions Status](https://github.com/ggml-org/whisper.cpp/workflows/CI/badge.svg)](https://github.com/ggml-org/whisper.cpp/actions)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![Conan Center](https://shields.io/conan/v/whisper-cpp)](https://conan.io/center/whisper-cpp)\n[![npm](https://img.shields.io/npm/v/whisper.cpp.svg)](https://www.npmjs.com/package/whisper.cpp/)\n\nStable: [v1.9.1](https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.1) / [Roadmap](https://github.com/orgs/ggml-org/projects/4/)\n\nHigh-performance inference of [OpenAI\u0027s Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model:\n\n- Plain C/C++ implementation without dependencies\n- Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and [Core ML](#core-ml-support)\n- AVX intrinsics support for x86 architectures\n- [VSX intrinsics support for POWER architectures](#power-vsx-intrinsics)\n- Mixed F16 / F32 precision\n- [Integer quantization support](#quantization)\n- Zero memory allocations at runtime\n- [Vulkan support](#vulkan-gpu-support)\n- Support for CPU-only inference\n- [Efficient GPU support for NVIDIA](#nvidia-gpu-support)\n- [AMD ROCm GPU support](#amd-rocm-gpu-support)\n- [OpenVINO Support](#openvino-support)\n- [Ascend NPU Support](#ascend-npu-support)\n- [Moore Threads GPU Support](#moore-threads-gpu-support)\n- [C-style API](https://github.com/ggml-org/whisper.cpp/blob/master/include/whisper.h)\n- [Voice Activity Detection (VAD)](#voice-activity-detection-vad)\n\nSupported platforms:\n\n- [x] Mac OS (Intel and Arm)\n- [x] [iOS](examples/whisper.objc)\n- [x] [Android](examples/whisper.android)\n- [x] [Java](bindings/java/README.md)\n- [x] Linux / [FreeBSD](https://github.com/ggml-org/whisper.cpp/issues/56#issuecomment-1350920264)\n- [x] [WebAssembly](ex",
  "github_repo": "ggml-org/whisper.cpp",
  "github_stars": 50904,
  "github_topics": [
    "inference",
    "openai",
    "speech-recognition",
    "speech-to-text",
    "transformer",
    "whisper"
  ],
  "homepage": "https://github.com/ggml-org/whisper.cpp",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 19313,
  "installs_365d": 64754,
  "installs_90d": 37583,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": "2026-06-20T23:43:37+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "whisper-cpp",
  "oldnames": [],
  "one_liner": "High-performance C/C++ inference engine for OpenAI\u0027s Whisper speech-to-text model with CPU and GPU acceleration.",
  "optional_dependencies": [],
  "rank_30d": 240,
  "rank_365d": 568,
  "rank_90d": 329,
  "raw_hash": "4012ffb7e44dd5cc",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/w/whisper-cpp.rb",
  "tap": "homebrew/core",
  "test_dependencies": [
    "pkgconf"
  ],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "1.9.1",
  "versioned_formulae": [],
  "why_use_this": "Transcribe audio to text locally and efficiently without cloud dependencies. Optimized for Apple Silicon, x86, and various GPUs with quantization support; significantly faster and more lightweight than Python implementations. Use this as a runtime dependency or standalone command-line tool for batch transcription workflows."
}