transcribe_video
Transcribe videos from YouTube, TikTok, Vimeo and 1000+ platforms or local files using OpenAI Whisper. Generate transcripts in TXT, JSON, and Markdown formats with support for 90+ languages.
Instructions
Transcribe videos from 1000+ platforms (YouTube, Vimeo, TikTok, Twitter, etc.) or local video files using OpenAI Whisper. Downloads/extracts audio and generates transcript in TXT, JSON, and Markdown formats. Requires yt-dlp, whisper, and ffmpeg to be installed.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Video URL from any supported platform (YouTube, Vimeo, TikTok, Twitter, Facebook, Instagram, Twitch, conference sites, and 1000+ more) OR absolute/relative path to a local video file (mp4, avi, mov, mkv, etc.) | |
| output_dir | No | Optional output directory path. Defaults to /root/Downloads/video-transcripts | |
| model | No | Whisper model to use. Larger models are more accurate but slower. Default: 'base' | |
| language | No | Language code (ISO 639-1: en, es, fr, de, etc.) or 'auto' for automatic detection. Default: 'auto' |