Private beta: we are looking for design partners
Video Context

Semantic video search

Find the moment,
not the file.

A video search API lets software search inside video content with a natural-language query, such as "the presenter explains pricing", and returns the matching moments with a video ID, a start time, an end time, and a confidence score.

REQUESTPOST /v1/search
const results = await vc.search({
  index: 'podcast-archive',
  query: 'every moment the guest talks about fundraising',
  limit: 5,
})
● ILLUSTRATIVE RESPONSEPREVIEW API
{
  "results": [
    {
      "video_id": "vid_31ab",
      "start": 82.14,
      "end": 96.31,
      "description": "Guest explains the seed round",
      "confidence": 0.96
    }
  ]
}

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

Search inside the video

File search finds a file by its name or its tags. Video search finds the moment. You ask a question in plain language, and the API returns start and end times.

Semantic video search finds moments by meaning. Keyword search finds only the exact words in a title, a tag, or a transcript. With semantic video search, the query “a goal from outside the box” finds the moment even if nobody says those words. The search uses what people say, what the camera shows, and the text on screen.

How it works

  1. You add videos to an index.
  2. Video Context extracts scenes, speech, on-screen text, and visual embeddings.
  3. You send a natural-language query.
  4. The API returns ranked moments with timestamps and a confidence score.

Where teams use it

  • Podcast and interview archives. Find every moment about one topic.
  • AI video editors. Find the right moment for an edit in seconds. See edit context.
  • Agents. Give an agent a tool that can answer “where in this video does X happen?”

FAQ

Questions, answered.

Common questions about semantic video search with Video Context.

What is semantic video search?+

Semantic video search finds moments in video by meaning, not by exact keywords. A query such as "someone opens a laptop" matches the visual action even if nobody says those words.

What is the difference between a video search API and semantic video search?+

Semantic video search is the method. It matches meaning, not exact words. A video search API is the service that gives this method to your software, with an index, a query endpoint, and results with timestamps.

Does video search use the transcript only?+

No. Video Context indexes speech, visual content, and on-screen text together, so a query can match what people say, what the camera shows, or both.

Is the Video Context API available now?+

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

Your videos contain
valuable data.
Start using it.

Analyse video at scale. Find exactly what you need. Give your products and AI the context to act on it.