Clipto - Fully local, natural language search over terabytes of media

@new_user___1282025165cc92287e7a197 Yes, that was exactly the Aha moment for me when I first tried it. I was editing a short drama series at the time, and I immediately felt how much time it could save：）

@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：）

@danielwayne Thanks Daniel!

@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.

@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.

Thanks, Joseph.@kjosephabraham 

That’s exactly how we think about it. We never started with “let’s add a local mode.” We started with the belief that some of the most valuable media people own should never have to leave their machines in the first place.

For many creators, studios, and teams, local processing isn’t just about privacy. It’s about maintaining ownership, reducing dependency on cloud infrastructure, and being able to work wherever the media is.

Really appreciate the support.

We think the future of AI will be local-first much more often than people expect.

@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.

@miladavaz Yes, absolutely！

macOS natively supports both SMB and NFS. You can mount your TrueNAS storage as a local directory via SMB or NFS, and then use it with Clipto.

The overall workflow is: TrueNAS for storage → Mount via SMB/NFS to Mac → Clipto indexes that path.

@bing7 A very good question!

Our search function does indeed support cross-language retrieval - for instance, if you search in Spanish, you can find video content that contains English dialogues.

The current implementation logic is feasible and can help you locate a large number of relevant results. However, the technical complexity of cross-language semantic matching makes its accuracy unable to fully match the search experience within a single language. Some expressions that are more colloquial and have strong cultural attributes may have a certain impact on the matching effect.

We are also continuously iterating to make cross-language search increasingly intelligent. If you have specific search scenarios, we can help you assess the expected results.

@lvyanghuang Yeah, that's a great point ~

The search results will show both timestamps and speaker labels.

The system first automatically detects different voice characteristics to distinguish between speakers (for example, labeling them as Speaker A, Speaker B).

Next, you can rename these speakers, changing them to names or roles.

Most importantly, this editing operation is globally effective — you only need to modify it once, and it will automatically apply to the recognition results of that same speaker across all media files, with no need for repeated setup.