Your video catalog,
as queryable data.

A video lakehouse stores a video catalog as structured, queryable data. Each video is segmented into scenes, shots, speakers, topics, and on-screen text, so a team can filter and search the whole library like tables instead of files.

Join the beta Use it from an agent

REQUESTPOST /v1/segments

const rows = await vc.segments.query({
  index: 'brand-archive',
  where: { type: 'shot', objects: ['product'], start_lt: 3 },
  select: ['video_id', 'start', 'end', 'thumbnail'],
})

● ILLUSTRATIVE RESPONSEPREVIEW API

{
  "rows": [
    { "video_id": "vid_0a91", "start": 0.0, "end": 2.4, "thumbnail": "…/0a91_0000.jpg" },
    { "video_id": "vid_77c2", "start": 0.6, "end": 2.9, "thumbnail": "…/77c2_0006.jpg" }
  ],
  "count": 212
}

This is the planned API design. Video Context is in private beta, and beta partners help set the final design of each endpoint.

Video is the biggest dataset you cannot query

Most teams store video as files in a bucket. The files have a name, a date, and maybe a few tags. Everything inside the video is invisible to search, to analytics, and to agents.

A video lakehouse changes that. Video Context segments every video and writes the result as rows:

video_id	type	start	end	labels
vid_0a91	shot	0.0	2.4	product, close-up, outdoor
vid_0a91	speech	2.4	9.8	speaker_1, pricing
vid_77c2	scene	0.0	31.2	unboxing, kitchen

What you can ask

Which ads show the product in the first three seconds?
Which interviews mention a competitor?
Which clips have a logo on screen, and for how long?

Built for scale

Segment once, and query many times. The same segments power search, templates, and auto-edit.

✦ FAQs

Frequently asked
questions

Common questions about video lakehouse with Video Context.

What is a video lakehouse?+

A video lakehouse keeps video files in storage and puts the structured context about them, such as segments, transcripts, objects, and embeddings, in queryable tables. You get the scale of a data lake and the query power of a warehouse, for video.

What is video segmentation?+

Video segmentation splits a video into meaningful parts, such as shots, scenes, speaker turns, and topics. Each segment gets a start time, an end time, and labels.

Is the Video Context API available now?+

Video Context is in private beta. Book a call with the team to get access.

Give your agent
eyes on video.

Private beta for teams that build video editors, agents, and catalogs. Book 30 minutes with the founders.

Join the beta Read agents.md