World Labs Marble API is one of 2 APIs that World Labs publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Marble. The published artifact set on APIs.io includes an OpenAPI specification.
This API exposes
9 operations
across 8 paths,
and defines 46 schemas.
It is described by OpenAPI 3.1.0, at version 1.0.0.
Requests are made against a single base URL, https://api.worldlabs.ai.
The identity and technical contract details declared by the specification.
VideoPrompt-Output
object
For world models supporting video (+ text) input.
3 properties
1 required
WorldAssets
object
Downloadable outputs of world generation.
5 properties
ExportWorldResult
object
Downloadable exported world asset.
5 properties
3 required
ListWorldsResponse
object
Response containing a list of API-generated worlds.
2 properties
1 required
Prompt
object
For world models generating a world from a single image (+ text). Images can be generated using the :image-generation method. If no text prompt is provided, it…
4 properties
1 required
MediaAsset
object
A user-uploaded media asset stored in managed storage. MediaAssets can be images, videos, or binary blobs that are used as input to world generation.
7 properties
4 required
ExportWorldResponse
object
Response from world export endpoint.
9 properties
2 required
SplatAssets
object
Gaussian splat asset URLs.
2 properties
WorldTextPrompt-Output
object
Input prompt class for text-conditioned world generation.
2 properties
PanoDepthToRgbRequest
object
Request to generate an RGB panorama from a depth panorama. Provide a depth panorama and a text prompt describing the desired appearance. The depth map supplies…
5 properties
2 required
MeshAssets
object
Mesh asset URLs.
3 properties
GenerateWorldResponse
object
Response from world generation endpoint.
9 properties
2 required
WorldTextPrompt-Input
object
Text-to-world generation. Generates a world from a text description. textprompt is REQUIRED.
3 properties
MultiImagePrompt-Output
object
For world models supporting multi-image (+ text) input.
4 properties
1 required
Permission
object
Access control permissions for a resource.
4 properties
SphericallyLocatedContent-Input
object
Content with a preferred location on the sphere.
2 properties
1 required
OperationCost
object
Settled credit cost for a successful operation.
2 properties
1 required
VideoPrompt-Input
object
Video-to-world generation. Generates a world from a video. textprompt is optional. Recommended video formats: mp4, webm, mov, avi. Maximum video size: 100MB.
4 properties
1 required
PanoDepthToRgbResult
object
Result from depth-to-RGB panorama generation. Returned inside Operation.response when the operation completes successfully (done=true).
1 property
ImageryAssets
object
Imagery asset URLs.
1 property
MultiImagePrompt-Input
object
Multi-image-to-world generation. Generates a world from multiple images. textprompt is optional. Recommended image formats: jpg, jpeg, png, webp.
5 properties
1 required
UriReference
object
Reference to content via a publicly accessible URL.
2 properties
1 required
MediaAssetPrepareUploadRequest
object
Request to prepare a media asset upload.
4 properties
2 required
SphericallyLocatedContent-Output
object
Content with a preferred location on the sphere.
4 properties
GetOperationResponse_Union_World__PanoDepthToRgbResult__ExportWorldResult__
object
9 properties
2 required
OperationCostLineItem
object
A single usage event contributing to an operation's total credits.
2 properties
2 required
MediaAssetPrepareUploadResponse
object
Response from preparing a media asset upload.
2 properties
2 required
MediaAssetKind
string
High-level media asset type.
Content
object
Represents content (media, text, images) that can be stored inline or via URL. Supports both direct data storage (up to 10MB) and URL references (up to 20MB).
3 properties
ValidationError
object
3 properties
3 required
DataBase64Reference
object
Reference to content via base64-encoded data.
3 properties
1 required
WorldsGenerateRequest
object
Request to generate a world from text, image, multi-image, or video input.
6 properties
1 required
MediaAssetReference
object
Reference to a previously uploaded MediaAsset.
2 properties
1 required
HTTPValidationError
object
1 property
Operation_PanoDepthToRgbResult_
object
9 properties
2 required
OperationError
object
Error information for a failed operation.
2 properties
WorldSemanticsMetadata
object
Semantic metadata describing how to interpret the generated splat asset in real-world units. The exported asset is in arbitrary model units. Apply the transfor…
2 properties
DeleteWorldResponse
object
Response from world deletion endpoint.
2 properties
2 required
InpaintPanoPrompt
object
For models that inpaint the masked portion of a pano image.
4 properties
2 required
ExportWorldRequest
object
Request to export a generated world asset.
4 properties
2 required
UploadUrlInfo
object
Information required to upload raw bytes directly to storage.
4 properties
2 required
World
object
A generated world, including asset URLs.
10 properties
3 required
ImagePrompt
object
Image-to-world generation. Generates a world from an image. textprompt is optional - if not provided, it will be generated via recaptioning. Recommended image…
5 properties
1 required
ListWorldsRequest
object
Request to list API-generated worlds with optional filters.
9 properties
DepthPanoPrompt
object
For models conditioned on a depth pano and text. When depthpanoimage is a log-encoded PNG, zmin and zmax are required to decode it correctly. When it is an EXR…
5 properties
1 required
The full machine-readable OpenAPI contract behind this narrative.
Other APIs World Labs publishes across the network.
