VisionAPI ReferenceV2

Trigger Captions

Dispatch VLM captioning on video chunks.

Authentication

X-Api-Keystring

API key authentication via X-Api-Key header

OR
AuthorizationBearer
Bearer token authentication via Authorization header

Path parameters

video_idstringRequired

Request

This endpoint expects an object.
forcebooleanOptionalDefaults to false
caption_promptstring or nullOptional

Response

Successful Response
video_idstring
featureenum
statusenum