cortexosmain

Would love that — issues are open and the codebase is small enough to read in one sitting. The areas I'd most welcome help on right now are additional transcript backends and smarter grid packing.

NotebookLM was transcript-only when I last checked. Gemini proper does ingest video natively (samples ~1fps server-side). This tool is for everything that can't — Claude, ChatGPT web, local models — it turns the video into frames + transcript on your machine so any of them can read it.

Took this — pip install llm-real-video works now, same tool. Kept the original repo name so existing links don't break.

Hi HN! I built this because I was frustrated that no LLM actually "sees" a video — Claude won't accept video files, ChatGPT reads the transcript only, and Gemini samples at a fixed 1fps (missing fast cuts, over-sampling static slides).

claude-real-video takes a URL or local file and:

1. Extracts frames at every scene change (not fixed intervals) + a density floor 2. Deduplicates with a sliding-window pixel-diff algorithm (so A-B-A interview cutaways don't re-send the same shot) 3. Transcribes audio (prefers embedded subtitles, falls back to Whisper) 4. Optionally keeps the full soundtrack for audio-capable models 5. Writes a clean MANIFEST.txt you can drop into any LLM chat

A 10-min presentation goes from ~600 fixed-interval frames to 5-15 meaningful keyframes. 90%+ token savings with better comprehension.

The dedup approach (v0.2.0) uses real pixel difference on 16x16 RGB thumbnails against a sliding window of the last N kept frames — inspired by videostil's pixelmatch, but simpler and self-contained.

`--report` generates a self-contained HTML showing every keep/drop decision with diff percentages, so you can tune the threshold visually.

pip install claude-real-video && crv "https://youtube.com/watch?v=..." --report

MIT licensed, pure Python + ffmpeg. Happy to answer questions!