Description

A tool and agent skill that enables Claude to analyze video by downloading content, extracting frames, and transcribing audio. It uses a pipeline of yt-dlp, ffmpeg, and Whisper to provide multimodal context, allowing agents like Claude Code to answer grounded questions based on visual and auditory information.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.