# jordanrendric/claude-video-vision

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

Repository: https://github.com/jordanrendric/claude-video-vision
Canonical: https://ross.abutalabs.com/products/claude-video-vision
Homepage: https://github.com/jordanrendric/claude-video-vision
Language: TypeScript
License: MIT
License Family: permissive
Topics: claude-code, claude-code-plugin, ffmpeg, gemini, mcp, mcp-server, multimodal, video-analysis, whisper
Last push: 2026-08-07T02:28:19+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 96, release rhythm 35, longevity 11
- inputs: {"age_days": 155, "days_push": 27, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1265, forks 152 (observed 2026-08-28T04:04:10.849890+00:00)

## What it is
A Claude Code plugin with an MCP server that gives Claude the ability to watch and understand videos by extracting frames via ffmpeg and transcribing audio via Gemini, local Whisper, or OpenAI backends. It supports local video files and YouTube URLs, adapting frame rate, resolution, and time ranges to the user's question.

## Use cases
- analyze a video file with claude
- summarize a youtube video
- transcribe audio from a video with timestamps
- extract frames from a video for claude to see
- find what text appears on screen at a timestamp
- understand a tutorial video's content
- process video locally offline with whisper

## When to choose
- you use Claude Code and want it to perceive video content
- you need flexible audio backends including fully local Whisper processing
- you want to analyze YouTube URLs directly with metadata and captions
- you want adaptive frame extraction tuned to your question

## When to avoid
- you need a standalone video analysis tool outside Claude Code
- you require deep video interpretation rather than a perception layer feeding Claude
- you cannot install ffmpeg and audio backend dependencies

## Facets
- artifact type: plugin
- maturity: active
- function: video-processing, speech-recognition, mcp, image-processing, nlp
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cli, cross-platform, windows
- tags: claude-code, mcp-server, ffmpeg, whisper, gemini, multimodal, youtube, frame-extraction, audio-transcription, video-analysis, video, nodejs, macos, linux

## Member repositories
- jordanrendric/claude-video-vision (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:10.849890+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:51.745600+00:00, confidence not recorded.
  - readme: https://github.com/jordanrendric/claude-video-vision (fetched 2026-08-28T04:04:10.849890+00:00, sha 37d581e5e9cf)
  - homepage: https://github.com/jordanrendric/claude-video-vision (fetched 2026-08-29T12:15:52.987135+00:00, sha 6b88bfcbae99)
  - registry_npm: https://registry.npmjs.org/claude-video-vision (fetched 2026-08-29T12:15:52.996597+00:00, sha 74e0435cbc36)
- Data as of 2026-08-30T08:39:29.467469+00:00.