<p>We've been honing Clipto's story for a few months. At the end of our last call <a href="https://www.producthunt.com/@henry_kang" data-node-type="mention" data-mention-type="user" data-mention-id="henry_kang" target="_blank" rel="nofollow noopener noreferrer">@henry_kang</a> proved the value of the product.</p><p></p><p>He and his team were out in the desert, <em>testing Clipto remotely</em>: minimal reception, terabytes of footage sitting on his laptop, and he needed to find a specific shot for the launch video.</p><p></p><p>He searched for: <em>"the wide drone shot where the car enters the desert"</em>. </p><p>He didn't want "a cinematic moment." Not a "vibes" search.</p><p></p><p>He <em>knew</em> he had the clip but in the pre-Clipto world, it would take hours of video scrubbing to find it. </p><p></p><p><strong>He found that clip in seconds using natural language to search over his own media, fully local. </strong></p><p><strong>Just like Google Photos — but nothing lives in the cloud.</strong></p><p></p><p>This isn't an easy problem to solve. Henry's been pursuing this direction for over twenty years, when at <a href="https://www.ri.cmu.edu/" target="_blank" rel="nofollow noopener noreferrer">CMU's Robotics Institute</a> (my alma mater, FYI), he began pushing the limits of computer vision. He starting with indexing hundreds of images and then advanced to <em>millions of objects</em> — and watched recognition basically explode once memory scaled. </p><p></p><p>Clipto is in many respects the culmination of that work, pointed at your personal hard drive.</p><p></p><p>And it's quick: a modern M5 MacBook chews through ~2TB of video in about a day. Why not push yours through its paces?</p>
<p>Hi Product Hunt! I’m Henry, founder of Clipto.</p><p></p><p><strong>Clipto gives you the ability to search in natural language over terabytes of media in seconds.</strong></p><p><strong>Think: Google Photos, but fully local.</strong></p><p></p><p>During my 20 years ago at <a href="https://www.ri.cmu.edu/" target="_blank" rel="nofollow noopener noreferrer">CMU’s Robotics Institute</a>, I became obsessed with memory systems: <em>what if computers could actually remember what they’ve seen?</em></p><p></p><p>I trained robots to memorize <em>millions</em> of product images crawled from the Amazon catalog (the standard back then was to index 100s of images at a time), and discovered that <em>they could use that memory to recognize almost anything they encountered!</em></p><p></p><p><strong>By pushing computers beyond their conventional limits, I had unlocked an explosion in machine intelligence.</strong></p><p></p><p>Years later, the problem has become personal.</p><p></p><p>Our computers are full of valuable raw footage, interviews, recordings, and more, but most of that data is still painfully hard to search, revisit, or reuse. <strong><em>We are data-rich, but knowledge-poor.</em></strong></p><p></p><p>That’s why I built Clipto. Clipto helps you find what matters inside terabytes of video, audio, meetings, and files, <em>instantly</em>, turning hours of repetitive work into seconds.</p><ul><li><p>Find the wide drone shot where the cars enter frame.</p></li><li><p>Find the shot specifically in the moment the sandstorm arrives from hours of footage.</p></li><li><p>And find what you <em>know</em> is in there, without suffering through hours of scrubbing.</p></li></ul><p>Clipto's memory system live where your data already is: on your device, under your control, available anytime, even offline — so you can keep working wherever and whenever inspiration strikes.</p><p></p><p><strong>After two years of compressing, optimizing, distilling and orchestrating AI models to run entirely on-device, we are ready to share it with the Product Hunt community.</strong></p><p></p><p>It’s still early, and it’s still compute-heavy. Right now, Clipto works best on higher-performance Apple Silicon Macs (M1 Pro/Max/Ultra and newer) with 24GB+ RAM. If you have a compatible Mac, we’d love for you to try it.</p><p></p><p><strong>To celebrate our launch, we're offering 1 month free to anyone who signs up this week with code PHLNCH.</strong></p><p></p><p>I’ll be here in the comments all day and would genuinely love to hear about the strategies you've developed to find your content diamonds in your digital rough.</p>
<p>This looks really interesting.</p><p></p><p>I'm curious about how deeply it understands media content.<br></p><p>Does it recognise things like camera angles, shot types (wide, medium, close-up), camera movements, transitions, B-roll, and multi-camera sequences?<br><br>It would be incredibly useful if I could search for something like "close-up shot of a person smiling" or "drone footage with a slow pan" and instantly find matching clips across my archive.<br></p><p>Would love to know how detailed the visual understanding gets beyond basic object and dialogue detection.</p>
