Skip to main content

​
Endpoint

Async — returns {id, status: "pending"}; poll GET /v1/videos/generations/{id} until success or failed.

​
Parameters

​
string
required
Text prompt describing how the first frame should be animated. Max 7000 characters.
​
string[]
required
A single-element array with the URL of the first-frame image to animate.
​
"5" | "6" | "7" | "8" | "9" | "10" | "11" | "12" | "13" | "14" | "15"
default:"\"6\""
Length of the generated clip in seconds. Drives the price (billed per second of output).
​
"480P" | "768P"
default:"\"768P\""
Output resolution. 480P bills at a lower per-second rate than 768P.
​
"adaptive" | "16:9" | "4:3" | "1:1" | "3:4" | "9:16" | "21:9"
default:"\"adaptive\""
Aspect ratio. adaptive follows the input image’s ratio.

​
Controlling the audio

There is no separate audio parameter — the same prompt that directs the shot also directs its sound. Describe the visuals first, then add a Sound: clause describing the track: ambience, individual effects, music, or spoken lines.
For a quiet clip, describe a quiet track (for example Sound: room tone, faint clock ticking). Audio is generated natively in sync with the picture and is included in the price — there is no way to switch it off with a parameter.

​
Example