AI Agent 分析

jordanrendric/claude-video-vision

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

Star

1.2k

语言

TypeScript

GitHub

来源与合规提示最近同步: Aug 9, 2026

Git-Stars 是独立产品，不隶属于 GitHub 或该项目。分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。我们不镜像完整 README、文档、Issue 或社媒评论。

原始 GitHub 来源方法论编辑政策

概览

Claude Video Vision is a Claude Code plugin that gives Claude the ability to perceive and understand videos by extracting frames via ffmpeg and transcribing audio through multiple backends (Gemini API, local Whisper, or OpenAI API). It acts as a perception layer, providing Claude with visual frames and timestamped audio transcriptions, enabling it to answer questions about video content directly within a coding session.

安装方式

Inside Claude Code, run: /plugin marketplace add https://github.com/jordanrendric/claude-video-vision then /plugin install claude-video-vision (MCP server auto-installs via npx).

解决的问题

This framework solves the problem of AI assistants lacking native video understanding by bridging the gap between video files and Claude's multimodal capabilities. It eliminates the need for manual frame extraction or separate transcription pipelines, allowing Claude to directly analyze video content in context, with adaptive extraction based on user queries.

可以构建什么

Developers can build workflows where Claude can analyze video tutorials, bug reports, lectures, or YouTube content directly from the command line. Use cases include summarizing long videos, extracting on-screen text, identifying code in tutorials, and answering questions about specific timestamps. The ceiling is high: with adaptive frame extraction and multiple audio backends, Claude can handle everything from quick clips to hour-long lectures, making it a versatile tool for video-based research, education, and debugging.

社区反馈

正向反馈

暂时没有社区反馈。

风险关注

暂时没有记录到风险关注。

结论

This plugin is ideal for developers who use Claude Code and need to analyze video content without leaving their terminal, offering flexibility in audio processing (cloud or local). It should be avoided by those who prefer a fully integrated GUI or who lack the required dependencies (ffmpeg, Node.js). The key trade-off is between convenience and setup complexity, with the plugin providing powerful perception but requiring initial configuration and external tools.

由 Git-Stars 分析 - 8/9/2026