Like Google Photos, but fully local. Turn the terabytes of video, audio, meetings, and files you work with into searchable memories, without uploading anything to the cloud. Clipto automatically tags people, dialogue, and scenes, so you can instantly find any moment buried in your media just by describing what you're looking for. It's fast too: on a MacBook Pro M5, Clipto indexed 2TB of videos in just 24 hours.
This is the 2nd launch from Clipto. View more
Clipto MCP
Launched this week
Clipto MCP gives Claude, ChatGPT, and other AI agents the ability to source clips and more from inside the videos, photos, and audio recordings stored on your computer.
Instead of manually browsing files, simply describe what you need. For example, turn a script into a video by matching each sentence with your local footage; find every scene where someone mentioned a topic; create rough cuts; or search years of media as if you have a dedicated assistant editor.
Free Options
Launch Team / Built With
Surgeflow
The “find this moment in my footage” use case is probably the first thing I’d try.
Clipto
@new_user___1282025165cc92287e7a197 That’s probably the best place to start :) Just describe whatever you remember about the moment, even if you have no idea which file it’s in. Thanks Yiyao!
Gro
I can see this fitting really naturally into an editing workflow. Find the right clips first, then build from there.
Clipto
@lily_liu8 Exactly. Finding the right clips is often the hardest part. Once agents can understand and source from your entire media library, there’s a lot more they can help with downstream. Thanks Lily!
Netlify
Sourcing clips from local video terabytes using AI agents is a huge time-saver. Congrats on bringing this to life!
Clipto
@thisiskp_ Thanks! That’s exactly the idea. Once a media library grows into terabytes, finding the right clip can take longer than editing it. We want agents to understand your entire library and bring back the right moment in seconds.
Readdy
For video editors, searching years of footage without remembering the exact filename is probably enough reason to try this.
Clipto
@wenjun_shi Exactly. You shouldn’t have to remember where a clip lives, or even when you shot it. Just describe what you remember about the moment and let Clipto find it. Thanks Wenjun!
Pokecut
Would love to see a longer version of the demo with a massive real-world media library.
Clipto
@anthony_cai Thanks Anthony, we tested on longer videos too and works pretty smoothly, actually we provided a demo library of 1000 royalty free clips so you can try it out on your agents as well. You can download it here: https://www.clipto.com/mcp/demo-library#footage-packs
This is so cool, I desperately needed something of this sort for so long
Clipto
@maunilparikh So glad this resonates. We built Clipto for exactly that feeling—knowing the moment exists somewhere in your library, but having no practical way to find it. We’ve included an invite code on our Product Hunt page that gives you a 30-day free trial. Give it a try and let us know what you think. Thanks Maunil!
Clipto
@maunilparikh Thanks! Please give it a try! Would love to see what you create!
Fish Audio
Clipto
Clipto
@hehe6z Coming from Fish Audio, that means a lot :) You’re doing some amazing work with AI voice. Clipto also understands speech and recognizes different speakers across local media, so it feels like there could be some really interesting ways for the two products to work together. We’d love to explore that in the future!
Fish Audio
@tizaolai886 that'd be fun!