xiaohui5206 /
let-ai-read-video
让任何 AI 真正"看"视频：纯本地的视频阅读 skill——faster-whisper GPU 转写 + ffmpeg 场景感知抽帧，双通道带时间戳（t=MM:SS），数据不出机。1 小时视频 3~5 分钟读完。Give any AI agent eyes for video: 100% local video-reading skill — faster-whisper GPU transcription + scene-aware ffmpeg frame extraction, dual-channel with t=MM:SS citations. Nothing leaves…
Updated 11 min ago
Why now
+14 stars gained this week
2× its usual pace
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A fully local video-reading tool that gives AI agents or users a timestamped transcript and scene-aware keyframes from Bilibili links, local files, or cache. Data never leaves the machine.
Summary written by AI from the repository’s description and README.
xiaohui5206 / let-ai-read-video
View on GitHub(opens in new tab)