Launched this week
Clipto
Fully local, natural language search over terabytes of media
793 followers
Fully local, natural language search over terabytes of media
793 followers
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.
KnowU
Finally, a tool that respects our privacy. Since it's 100% local, does that mean absolutely zero data or telemetry is sent back to your servers?
Clipto
@carlvert That's exactly right for 100% on-device processing, no data leaves your machine, no telemetry, nothing. That's the whole point of that mode.
If you choose Hybrid mode, some minimal data is used to enable cloud features like sync and collaboration — but that's opt-in, and clearly labeled when you set it up. Your choice, fully in your control：）
@carlvert @matthewwei How you track the performance of your product then? What if something went wrong or your users does not like it ?
Clipto
@carlvert @sabber_ahamed We have multiple user feedback channels in place to ensure we receive and address user issues as quickly as possible.
When something goes wrong , we step in immediately under the premise of information confidentiality.
All troubleshooting and solutions are carried out only with the user's explicit authorization.
Once authorized, our technical engineers will investigate the issue and work to resolve it promptly.
We take all user needs and suggestions seriously — every piece of feedback is heard, recorded, and used to drive continuous improvement.
@carlvert @matthewwei Since no data leaves users' devices, you don't receive any information about the system unless users report + authorize issues through the feedback channel, right ?
Kollab
Does it support a simple drag-and-drop workflow for mass importing terabytes of media? My current desktop storage is an absolute disaster.
Clipto
@yan_labs_ Yes.Just select all your folders and drag them straight into Clipto — no reorganizing needed beforehand. Clipto will analyze your video and audio files and automatically tag them across multiple dimensions: people, dialogue, scenes, objects, and more. So when you're looking for something later, just describe what you remember about the content, and Clipto will find it instantly.
A couple of quick notes:
Clipto reads your files where they already live — it won't move, reorganize, or delete anything. Your files stay exactly where they are.
Indexing speed depends on your Mac's specs. On an M5 MacBook Pro, ~2TB takes about a day. Higher-end chips (M1 Pro/Max/Ultra and above with 24GB+ RAM) will give you the best experience.
Pandada AI
As a creator signing strict NDAs for commercial projects, cloud tools are out of the question. Is there really no cloud rendering or uploading involved at all?
Clipto
@panwangqun Yes, Clipto is built around local-first processing. Your media analysis and search run on your device, so your footage doesn’t need to be uploaded to the cloud or rendered on our servers. For NDA-sensitive projects, you can even keep the workflow fully offline and use Clipto without an internet connection. Hope Clipto can help with that：）
DeckSpeed
Is there a maximum file size or duration limit for a single clip? I frequently work with 3-hour long uncompressed theater recordings and want to make sure the local database won't crash during indexing
Clipto
@hanzhizhang0405 There isn’t a fixed file size or duration limit for a single clip.For long recordings like a 3-hour theater capture, Clipto can index them, but the processing time will depend on your machine and the length of the video.
One useful note: under the same device conditions, Clipto’s content understanding speed is usually more related to video duration than file size. File size can matter in some cases, like when transcoding is involved, but it’s usually not the main factor.
Surgeflow
If I have duplicate files or very similar takes of the same scene, how does Clipto display them in the search results? Does it group them together?
Clipto
@zephyrlink_i Great question.
Exact duplicate files are automatically deduplicated during indexing, so we don’t process or store the same file multiple times.
For similar takes, alternate angles, or near-duplicate shots, we currently keep them as separate results and rank them based on relevance to the search query.
In practice, that’s often what creators want. When you’re editing, multiple takes of the same scene can have subtle differences in framing, timing, performance, or camera movement, so seeing several strong matches side-by-side helps you quickly compare and choose the best shot.
That said, grouping similar results is something we’re actively exploring, especially for large productions with hundreds of takes. We think there’s a balance between reducing clutter and preserving creative choice.
YourAIScroll
Is there a way to add manual tags or notes on top of the AI descriptions to customize the search for a specific client project?
Clipto
@zhengyang_hou Clipto uses auto-tagging by default.
The AI analyzes every media file you drag and drop — and automatically generates tags based on the content of your files. This makes it easy to search by tag right away.
Very cool Idea!! If it woks fully in local, you must be using small LLM/VLM on local device. In that case do you see any memory Or CPU issues? How do you fix that ?
Clipto
@sabber_ahamed That's a great question.
First, choose a smaller model.
Second, slim it down through optimization.
Finally, schedule tasks flexibly based on how busy your computer is — that is, 'model miniaturization itself, compression optimization, and flexible task scheduling based on the user's machine usage.