{
  "name": "audio-transcribe",
  "type": "skill",
  "category": "media",
  "version": "1.0.0",
  "released": "2026-10-13",
  "page": "https://agent-toolkit.itqanlab.com/s/audio-transcribe/",
  "changelog": "https://agent-toolkit.itqanlab.com/s/audio-transcribe/CHANGELOG.md",
  "releases": [
    {
      "version": "1.0.0",
      "date": "2026-10-13",
      "breaking": false,
      "changes": {
        "Added": [
          "Transcribe a local audio or video file, a direct media link, or a YouTube or other site link, fully on this machine.",
          "Arabic (including Egyptian dialect), English, or automatic language detection.",
          "Plain text, SRT and VTT subtitles, or JSON with timings.",
          "Uses the fastest local Whisper engine installed: mlx-whisper on Apple Silicon, whisper-ctranslate2 or openai-whisper elsewhere.",
          "A model is never downloaded without first saying how big it is.",
          "Warns when the audio is near-silent, because Whisper invents text over silence.",
          "Retries once with the large model when the output falls into a repetition loop.",
          "A dependency check that shows the install commands and asks before running them, on macOS, Linux and Windows."
        ]
      }
    }
  ]
}