Type what you're looking for in plain language. Search video by scene, color, or description and FrameQuery matches your query against every frame in your library using SigLIP visual embeddings and MiniLM transcript embeddings. It also powers reverse video search across your own footage.
Optional models with CUDA or Metal acceleration and CPU fallback.
3 results · 12ms
A001_C003.mov
VisualB_ROLL_LAKE.mp4
TranscriptINTERVIEW_EXT.mov
ObjectWorks with
your workflow.
Exports to your NLE. Reads cinema RAW natively.
Visual search and semantic transcript search run simultaneously when you type a query. Results are ranked by combined relevance so the best matches surface first.
SigLIP handles image-text matching, comparing your query against every frame in your library.
MiniLM handles semantic text similarity, so transcript matches are found by meaning.
Both run on every query, and results are ranked by combined relevance.
Click “Find Similar” on any scene card to search for visually similar scenes across your library. Uses cosine distance between SigLIP embeddings to rank results by visual similarity.
Source Scene
An aerial view shows a vast, dry grassland dotted with scattered trees and rounded hills under a bright, cloudy sky.
A vast golden field of dry grass with a dirt road cutting through, leading towards distant rolling hills.
Savannah landscape with scattered acacia trees stretching to the horizon under golden afternoon light.
A large herd of animals moving in a winding line across dry grassland with scattered trees.
Wide aerial shot of river winding through arid plains at dusk with long shadows.
Searching runs on your machine and works offline. Colour and similar-shot matching use on-device SigLIP embeddings; scene descriptions and object tags are created when a video is indexed.
Search video by color to find scenes that match a specific palette.
Search by scene description to locate the right mood, setting, or composition.
Object detection tags every scene with what appears on screen, so you can search for “laptop” or “car” directly.
Find visually similar shots by clicking any scene card.
SigLIP handles image-text matching, MiniLM handles semantic text similarity. Your search index works without them (keyword search only) until you choose to enable visual search.
Visual search models are optional and download on demand.
Both are ONNX format and run with CUDA or Metal acceleration when available, with CPU fallback.
Until you enable visual search, your search index keeps working with keyword search only.
How matching works, finding similar shots, and what the models need.
Type what you're looking for in plain language and FrameQuery matches it against every frame in your library.
Visual search models are optional and download on demand.
