algoprog/transcribe

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "transcribe",
  "version": "1.1.0",
  "description": "Speech to text on this computer with Whisper (faster-whisper): recordings, voice notes, videos and podcasts become text and subtitles, in about 100 languages, without sending the audio anywhere. It runs on an NVIDIA graphics card when there is one, else on the CPU.",
  "author": { "name": "Hydor Devs", "url": "https://hydor.app" },
  "license": "Apache-2.0",
  "keywords": ["transcription", "speech to text", "whisper", "subtitles", "audio"],
  "extensions": {
    "com.naget.agent": {
      "title": "Speech to text",
      "category": "creative",
      "icon": "mic",
      "requires": {
        "plugins": { "media-tools": "^1.0.0" },
        "python": ">=3.10",
        "pip": ["faster-whisper>=1.1,<2"],
        "pipNvidia": ["nvidia-cublas-cu12>=12,<13", "nvidia-cudnn-cu12>=9,<10"]
      }
    }
  }
}