Turn hours of video into text your product can use. For every video you send, get the full transcript and a two-paragraph summary of what happens.

How it works

  1. Send video URLs in batches of up to 500.
  2. Get the transcript and summary for every video, alongside any other signals you choose.
  3. Index or display them: in search, in editorial tools, or as input to your own models.

What comes back

{"type": "TRANSCRIPTION", "transcript": "Look into my eyes. Feel my energy..."}
{"type": "SUMMARIZE", "result": {"summary": "The video shows a playful hypnosis attempt intended to make someone forget a movie..."}}

What teams build with it

  • Library search and discovery: find the video that answers the question.
  • Editorial and newsroom tooling: summaries for every clip in the feed.
  • Input for downstream models: clean text from video for your own pipelines.

Frequently asked questions

How long is the summary?

Two paragraphs per video.

Can I get a summary and categories in one call?

Yes. Choose all the signals you need for each batch.

Whose models, and at what scale

Our own models, trained and curated in-house by advertising and media people, so we can tune them to your needs. Your video isn't sent to a big LLM provider.

Built for libraries and feeds: our infrastructure processes 100k+ videos per hour.

New signals added regularly. Custom models on request.

Ready to test it on your own video? Get API access.