Claude Code ecosystem

claude-video-vision

Let your assistant actually watch the video

Visit official page 日本語で詳しく見る

Popularity

★ 1.2k

Last update

August 2026

License / pricing

MIT

What it does

A Claude Code plugin that extracts frames with ffmpeg and transcribes audio with timestamps — Gemini, OpenAI or local Whisper — handing both to the model. YouTube URLs work directly via yt-dlp. It deliberately stops at perception: the interpretation is the model's. Frames and transcript go wherever your backends point, which matters for recorded meetings and anyone else who appears in them, and sampling too sparsely means the model simply never sees the moment you asked about. MIT.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

Setup difficultySome setup needed
Command lineRequired
API keyRequired
Sends data onlineYes

Judged automatically from the project's own metadata. Always confirm on the official page.

claude-video-vision FAQ

Is claude-video-vision free?: claude-video-vision itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.
Do I need to install anything or write code to use claude-video-vision?: It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
Does claude-video-vision work on a phone?: No. It needs a computer.
Can I use claude-video-vision commercially?: The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
claude-video-vision (this page)	Required	Required	Yes	No	Yes
claude-real-video	Required	Not needed	No	No	Yes
Claude Code	Required	Required	Yes	No	Not verified
taste-skill	Required	Required	Yes	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other claude code ecosystem tools

claude-real-video

Prepares a video so a model actually sees what changed

Claude Code

Anthropic's AI coding partner that lives in your terminal

taste-skill

Skills that stop AI-built interfaces from looking like every other one

rtk

Compresses command output before your agent pays to read it

Browse all tools Home

What it does

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

claude-video-vision FAQ

Is claude-video-vision free?

claude-video-vision itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.

Do I need to install anything or write code to use claude-video-vision?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does claude-video-vision work on a phone?

No. It needs a computer.

Can I use claude-video-vision commercially?

The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
claude-video-vision (this page)	Required	Required	Yes	No	Yes
claude-real-video	Required	Not needed	No	No	Yes
Claude Code	Required	Required	Yes	No	Not verified
taste-skill	Required	Required	Yes	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.