Video analysis with artificial intelligence
Claude-video is a Python tool that gives the Claude model the ability to analyze video content. By downloading videos, dividing them into frames and converting them into text (transcription), the software brings the visual data into a format that the artificial intelligence model can process.
Updates
- August 31, 2026: Stars 15,503 → 16,553, latest release v0.2.0 (July 1, 2026).
- August 15, 2026: Stars 14,427 → 15,503, latest release v0.2.0 (July 1, 2026).
- August 7, 2026: Stars 13,424 → 14,427, latest release v0.2.0 (July 1, 2026).
- August 2, 2026: Stars 4,554 → 13,424, latest release v0.2.0 (July 1, 2026).
What you get
- Analyzes videos frame by frame
- Automatically produces subtitles and transcripts
- Processes local or online videos
Installation
npx skills add bradautomates/claude-video -gRunning it
/watch https://youtu.be/dQw4w9WgXcQ what happens at the 30 second mark?If you don't write code
I want you to analyze the video I shared using the Claude Video tool. Answer the content of the video, its important moments and the questions I ask, based on the visual frames in the video and the audio transcript. If there is no subtitle in the video, convert the audio to text using Whisper API and analyze it by examining the visual details (frames).
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-07: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.