Video Processor
Downloads, converts, and transcribes video content from YouTube and other platforms using yt-dlp, FFmpeg, and Whisper AI.
The Video Processor skill provides a unified interface for complex multimedia workflows, allowing users to seamlessly download videos from thousands of websites, extract high-quality audio, and perform AI-driven transcriptions. By integrating yt-dlp, FFmpeg, and OpenAI's Whisper model, it enables automated format conversion to MP4 or WebM and generates subtitles in various formats like SRT, VTT, and JSON. This skill is ideal for developers and content creators who need to batch-process video assets or extract textual data from multimedia content directly within their Claude Code environment.
主要功能
01Automated audio extraction and optimization for transcription workflows
02High-performance video conversion to web-optimized MP4 and WebM formats
03232 GitHub stars
04AI-powered speech-to-text using Whisper with adjustable model sizes
05Universal video downloading from 1000+ sites via yt-dlp integration
06Multi-format subtitle generation including SRT, VTT, and timestamped JSON
使用场景
01Converting legacy video files into modern, web-ready formats with optimized compression
02Downloading and archiving educational videos or research material for local analysis
03Generating accurate transcriptions and subtitles for interviews, lectures, or social media content