Video Head Swap analysis by SpicyAPI is the first of two calls. It tracks every head in a 5 to 30 second clip at 480p or 720p and returns one numbered preview still per head, which the swap call then uses. It does not change the video.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
Outputrooftop-two-heads Two heads seen from behind, shoulder against shoulder, is deliberately the ambiguous case: a tracker that cannot separate them will return them in an unstable order. What comes back is one preview still per head with a fixed index, and that index is what the swap call consumes. Run the analysis at `resolution` `480p` — the stills exist so you can identify heads, not to be delivered, and the swap call takes its own resolution.
- 480p
- No sample yet
crowd-scene-scan A short clip with more than one person on screen, analysed at 720p. What comes back is one preview still per tracked head, in order, so position 0 is the first image. Nothing in the clip itself is changed. The footage is synthetic.
- 720p
This example starts at $0.08 per request. The Playground updates the estimate when you change the settings.