An auto-edit API uses video understanding to make edit decisions automatically. It finds the best moments, removes silences and filler, and returns a timeline or edit decision list that a video editor or an agent can render.
This is the planned API design. Video Context is in private beta, and beta partners help set the final design of each endpoint.
Editors need context, not only pixels
An AI video editor cannot cut well if it does not know what is in the footage. It needs to know where the speaker pauses, which moment is the strongest, where the faces are, and when the topic changes.
Video Context gives the editor that knowledge as data. The editor, or the agent that drives it, then makes the cut.
What auto-edit can do
Highlights. Find the best moments for a length and a platform.
Silence and filler removal. Cut dead air, “um”, and false starts.
Reframe. Follow the speaker when you change 16:9 to 9:16.
Assemble. Build a first cut from a goal in plain language.
Output that fits your stack
The result is a timeline in JSON, or an EDL. It works with web editors, desktop editors, and cloud render pipelines.
✦ FAQs
Frequently asked questions
Common questions about auto-edit with Video Context.
What is an auto-edit API?+
An auto-edit API makes edit decisions from video context. It picks clips, sets in and out points, reframes the shot, and returns a timeline that a renderer can play or export.
Does Video Context render the video?+
Video Context returns the edit decisions as timeline JSON or an EDL. You render with your own editor or pipeline, so you keep control of the output.
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.