aintoniodev/video-to-text

v1.0.0MIT

Extract transcript text from videos (TikTok, YouTube, Instagram, X, any URL) or local video files — fully local, no API keys. Ships scripts/vxtract.py: yt-dlp download + ffmpeg audio extraction + faster-whisper transcription (Spanish/English/auto, CPU or CUDA) with .txt/.md/.srt output. Alternative to cloud transcription services.

GitHub

What this package declares

The file a client reads when it loads this plugin, exactly as this revision carries it.

plugin.json

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "video-to-text",
  "version": "1.0.0",
  "description": "Extract transcript text from videos (TikTok, YouTube, Instagram, X, any URL) or local video files — fully local, no API keys. Ships scripts/vxtract.py: yt-dlp download + ffmpeg audio extraction + faster-whisper transcription (Spanish/English/auto, CPU or CUDA) with .txt/.md/.srt output. Alternative to cloud transcription services.",
  "author": {
    "name": "Antonio Gómez"
  },
  "license": "MIT",
  "keywords": [
    "transcription",
    "subtitles",
    "whisper",
    "video",
    "tiktok",
    "youtube",
    "speech-to-text",
    "stt",
    "yt-dlp"
  ],
  "extensions": {}
}

What else this package ships

These files come with the package and this site does not publish them. They are listed so you know what is there before you install it.

vxtract.py

View on GitHub