Your LLM can't actually watch video. Here's the smallest fix (MIT)

A developer built claude-real-video, an MIT-licensed tool that converts video files into formats LLMs can genuinely process, addressing the gap where models like ChatGPT and Claude fail to handle actual video content. The tool extracts audio via faster-whisper, samples frames with adaptive thresholds for slow deformations, and anchors frames at subtitle cues to capture on-screen text. It has gained 1,731 stars and ~8k monthly installs, running locally without intermediary APIs.

Every model card says "multimodal". Then you hand the model a real video file and discover what that means in practice: ChatGPT reads the subtitle track, Claude doesn't accept video files at all. The model narrates a video it mostly never saw. I unpack viral videos daily for my own content work, so I couldn't route around this. I built a small tool instead. claude-real-video converts a video into three things an LLM can genuinely read: --adaptive flag handles slow deformations a real user bug report: fixed thresholds missed squash/stretch morphs entirely . faster-whisper is installed it runs in-process and several times faster, with automatic fallback. --text-anchors flag force-samples frames at subtitle cues so on-screen text never falls between frames.Then you point any LLM at the output folder — Claude, GPT, Gemini, or a local model. No API of mine in the middle, everything runs on your machine. pip install claude-real-video crv "video.mp4" -o out Not real-time — a 90-second video takes about 1–2 minutes all-in on an M-series Mac. Frame sampling can still miss motion between frames; the flags above patch the worst cases, both born from real GitHub issues. It's MIT, currently at 1,731 stars with ~8k installs last month, which taught me the problem was never just mine: https://github.com/HUANGCHIHHUNGLeo/claude-real-video https://github.com/HUANGCHIHHUNGLeo/claude-real-video