generateVideo
Generate a video from a text prompt using an AI model.
mindstudio.generateVideo({ prompt }) → Result
Generates a video from a text prompt, and optionally a start image, returning a hosted video URL, with a model override selecting the model and its options. Generation is slow — fire it from a background task and update the record when it lands, rather than blocking the request.
Parameters
prompt
string
RequiredText prompt describing the video to generate
intermediateAsset
boolean
When true, the asset is created but hidden from the user's gallery (tagged as intermediate)
videoModelOverride
object
Optional model configuration override. Uses the workflow's default video model if not specified
generateVariants
boolean
Whether to generate multiple video variants in parallel
numVariants
number
Number of variants to generate (max 10)
addWatermark
boolean
Whether to add a MindStudio watermark to the generated video.
The watermark is a product mark on assets generated in the MindStudio UI. A step run directly via the SDK or API is producing the app's own asset, so it is never watermarked and
Call from a method
import { mindstudio } from '@mindstudio-ai/agent'; const result = await mindstudio.generateVideo({ prompt: /* ... */ });