01 Evidence across work files
Findcub
Find pages, timestamps and original evidence in complex work files on your Mac.
Discover Findcub MULTIMODAL SEARCH INFRASTRUCTURE
Multimodal intelligence.Built for search.
The foundation for multimodal intelligence—making data searchable and reusable.
01 / MULTIMODAL MODELS
OmniSpectra
Encode multimodal content into comparable vectors, connecting data by meaning.
OmniSpectra Edge
On-device versionAn on-device version of OmniSpectra for local inference.
Documents, images, video, audio and text are inputs to OmniSpectra, which encodes them into vectors. Content text and query text use the same encoder and are related by meaning in a shared semantic space. The content and vector positions are illustrative.
Content Query example· Text
- Wind energy Documents
-
Image - Video
- “Wind power” Audio
- Turbine checks Text
Offshore wind power
Shared semantic space
02 / PRODUCTS
Multimodal search. Made for your workflow.
02 Video archive search
ShotAI
Find reusable shots across video archives and projects, built for production and post teams.
Discover ShotAI