This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Paste a YouTube link into ChatGPT and it reads the transcript, not the picture. crv runs locally: scene-change detection picks the frames that matter, dedup drops the repeats, Whisper transcribes the audio - then any LLM can read the folder. MIT, no ML downloads.
Hey PH! I'm Leo, a non-engineer from Taiwan.
I kept pasting YouTube links into AI chats and realizing they only read the transcript. The picture - the cuts, the pacing, the visual hooks - was invisible.
So I built crv with Claude Code. It grabs a frame at every scene change (not a fixed 1 fps), throws away near-duplicates, and transcribes the audio. Everything runs on your machine. On a 58-second test clip that's 26 frames instead of 58, with nothing missed.
It hit the Hacker News front page last week and just passed 700 stars, which still feels unreal. There's also a bundled Claude Code skill: paste a video link into the chat and Claude watches it by itself.
It's MIT and `pip install claude-real-video`. Ask me anything - especially where it breaks. :)
how does the scene-change detection actually figure out which frames matter across different video styles like fast cuts versus long talking heads?
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?
How does the scene-change detection actually figure out which frames matter without downloading a full model, and does it handle videos with lots of fast cuts or mostly static screencasts equally well?
Ran it on a long cooking video and the scene-change detection actually pulled the useful moments instead of every other frame. Whisper nailed the audio too, no setup headaches.
About claude-real-video on Product Hunt
“Let Claude - or any LLM - actually watch a video”
claude-real-video was submitted on Product Hunt and earned 7 upvotes and 10 comments, placing #51 on the daily leaderboard. Paste a YouTube link into ChatGPT and it reads the transcript, not the picture. crv runs locally: scene-change detection picks the frames that matter, dedup drops the repeats, Whisper transcribes the audio - then any LLM can read the folder. MIT, no ML downloads.
claude-real-video was featured in Open Source (68.6k followers), Developer Tools (515.5k followers), Artificial Intelligence (473.1k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 218.1k products, making this a competitive space to launch in.
Who hunted claude-real-video?
claude-real-video was hunted by HUANGCHIHHUNG. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how claude-real-video stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
HUANGCHIHHUNG