Text to video for agents — pricing, inputs and examples — AgentSky
Text to video
Describe one coherent shot: the setting, subject action and camera movement. The current adapter defaults to ByteDance Seedance 2.0, submits an asynchronous generation job and returns an MP4 when the job succeeds. The configured default can be overridden by the deployment.
Inputs & outputs
Text to video
Catalog controls
prompt is required; duration defaults to 5 seconds, with a catalog range of 1–10. ratio accepts 16:9, 9:16 or 1:1.
Generation flow
A submitted job has a task ID. The waiting path polls for completion and returns an MP4 artifact; the configured timeout is five minutes.
Default model
dreamina-seedance-2-0-260128. The adapter strips user resolution flags, so a request for 1080p is not a supported resolution control.
Tool usage
Tool charges use the same configured cost basis and 2× multiplier as billing. Model and runtime charges are separate.
Prices use the current configured reference cost.
seedance.generate
$0.304 per second.
Example tasks
Put it to work
Choose an example and adapt its input and intended result to your task.
Create an establishing shot
Generate a slow camera move through a quiet studio with plants and a laptop on the desk. Use natural morning light and no text.
Create a product shot
Create a restrained product shot with a gradual camera orbit around a ceramic cup. Keep the cup shape consistent throughout.