{
  "slug": "whisper",
  "name": "Whisper",
  "aliases": ["openai-whisper", "OpenAI Whisper"],
  "vendor": { "name": "OpenAI", "slug": "openai", "website": "https://developers.openai.com/api/docs" },
  "homepage_url": "https://github.com/openai/whisper",
  "docs_url": "https://github.com/openai/whisper",
  "repo_url": "https://github.com/openai/whisper",
  "license_url": "https://github.com/openai/whisper/blob/main/LICENSE",
  "product_type": "model",
  "product_status": "maintenance",
  "summary": "OpenAI's open-source multilingual speech recognition model family with MIT-licensed code and weights, a Python package and CLI for transcription, translation and language identification",
  "description": "Whisper is a general-purpose speech recognition model released by OpenAI in 2022 with code and weights under the MIT license. A single Transformer sequence-to-sequence model trained on a large, diverse audio corpus performs multilingual transcription, translation into English and language identification. Six sizes are published, from tiny to large, plus turbo, an optimized variant of large-v3 that trades a little accuracy for speed and is not trained for translation; English-only variants exist for the smaller sizes. The `openai-whisper` Python package exposes `load_model` and `transcribe`, and a `whisper` CLI handles files directly; dependencies are PyTorch, tiktoken and ffmpeg.\n\nWhisper is the foundation of a large downstream ecosystem: faster-whisper and whisper.cpp reimplement inference for CPUs and small devices, mlx-whisper ports it to Apple Silicon, and OpenAI's hosted transcription API offers the same capability without local setup. The original repository changes infrequently and serves mainly as a reference, so projects needing speed or long-form robustness usually pick one of the derivatives. Accuracy varies substantially by language and audio quality, timestamps are approximate, and speaker diarization is not included.",
  "capabilities": ["Multilingual transcription and translation to English", "Automatic language identification", "Six model sizes plus turbo for faster inference", "Python API and CLI", "MIT-licensed weights usable in derivative runtimes"],
  "workflows": ["Transcribe lecture recordings offline with the CLI", "Pick a model size to balance accuracy and speed on available hardware", "Swap to mlx-whisper or faster-whisper for production throughput"],
  "advantages": ["Permissive MIT license for code and weights", "Strong multilingual coverage", "Large ecosystem of optimized reimplementations"],
  "limitations": ["Reference implementation is slow compared with derivatives", "No speaker diarization and approximate timestamps", "Accuracy drops on low-resource languages and noisy audio"],
  "prerequisites": ["Python with PyTorch and ffmpeg", "GPU recommended for larger models"],
  "audiences": ["Researchers and students transcribing interviews or lectures", "Developers embedding speech recognition offline"],
  "alternatives": ["mlx-whisper", "elevenlabs", "openai-platform"],
  "categories": [{ "slug": "speech-vision-multimodal", "primary": true }],
  "tags": ["speech", "open-source", "python", "cli", "transcription", "model"],
  "use_cases": ["run-local-models"],
  "operating_systems": ["macos", "linux", "windows"],
  "execution_modes": ["local"],
  "interfaces": ["cli", "library"],
  "deployment_models": ["embedded"],
  "integrations": ["PyTorch", "ffmpeg", "mlx-whisper", "whisper.cpp", "faster-whisper"],
  "data_formats": ["MP3", "WAV", "M4A", "FLAC", "SRT/VTT output"],
  "languages": ["Python"],
  "source_model": "open-source",
  "license_spdx": "MIT",
  "pricing_model": ["open-source", "free"],
  "self_hostable": true,
  "sources": [
    { "url": "https://github.com/openai/whisper", "type": "official_site", "title": "openai/whisper", "supports": ["name", "summary", "capabilities", "prerequisites"], "checked_at": "2026-11-02", "note": "The announcement page on openai.com returns 403 to automated clients; the repository is the canonical reference" },
    { "url": "https://github.com/openai/whisper", "type": "repository", "supports": ["license_spdx", "languages"], "checked_at": "2026-11-02" },
    { "url": "https://github.com/openai/whisper/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" }
  ],
  "confidence": "high",
  "uncertainty_note": "product_status is set to maintenance because the repository receives infrequent updates and the README carries no roadmap; OpenAI has not declared it deprecated.",
  "discovery_method": "editorial-research",
  "depth": "standard",
  "editorial_status": "reviewed",
  "visibility": "public",
  "featured": false,
  "author": "batch-A"
}