claude-real-video
Let Claude — or any LLM — actually watch a video
14 followers
Let Claude — or any LLM — actually watch a video
14 followers
Open-source CLI that turns any video into scene-aware keyframes and a timestamped transcript, processed locally. New since the first launch: exact per-frame timestamps, faster-whisper transcription, a trilingual interactive viewer, and honest dedup for slow-changing footage.
How does the scene-change detection decide which frames actually matter, and can I tweak the threshold if it's pulling too much or too little from longer videos?
@ercan1811695 Yes - the --scene flag is exactly that dial (default 0.30, lower = more frames). Long videos usually want a slightly higher threshold plus --grid to pack survivors into contact sheets so token cost stays flat.
how does the scene-change detection actually figure out which frames matter across different video styles like fast cuts versus long talking heads?
@layda147365 Different failure modes: fast cuts give you lots of frames (dedup then collapses the repeats), talking heads barely change so the density floor guarantees you still get periodic frames, and the transcript carries most of the meaning there anyway.