Detect Scene Changes in a Video
List the timestamps where the picture cuts to a new scene, then pick trim, split and clip boundaries from real cuts. Run the preset directly on this page or call the same agent-ready endpoint from your product.
See what the tool changes.
A real example: the after side is the unedited output of a KinoPipe job. Run the live form above to generate the same result from your own media.
Demo footage: public-domain timelapses (Bureau of Land Management, Oregon · NASA SVS). Processed by the same pipeline the API and MCP tools call.
Useful defaults, typed options.
The tool slug stays stable while your agent supplies named media inputs and a narrow set of documented options.
- No encode, analysis only
- Adjustable sensitivity
- Feeds trim, split and clip calls
- 01Decode the video stream
- 02Score every frame for scene change
- 03Keep frames above the threshold
- 04Return timestamps as JSON
POST /api/v1/tools/detect-scenesKnow the boundaries before you run.
About detect scenes
What does the threshold change?
Each frame gets a 0-1 scene-change score; frames above the threshold are reported. 0.3 finds standard cuts, lower values also catch soft transitions.
How do I use the result?
The job returns sceneChanges as a JSON array of seconds. Pass them straight to trim-video, split-video or create-social-video-clip.