Skip to main content
POST
For all supported video domains, see the Hub Catalog.

Try our Colab Cookbook Example

Try our Colab Cookbook example for long-form video transcription.

Example Output

Example Video Transcription

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request to the Video API (i.e. structured prediction).

metadata
RequestMetadata · object

Optional metadata to pass to the model.

config
GenerationConfig · object

The VLM generation config to be used for //generate.

url
string | null

The URL of the file (provide either file_id or url).

file_id
string | null

The ID of the uploaded file (provide either file_id or url).

id
string

Unique identifier of the request.

created_at
string<date-time>

Date and time when the request was created (in UTC timezone)

callback_url
string<uri> | null

The URL to call when the request is completed.

Minimum string length: 1
model
default:vlm-1

The model to use for generating the response.

Available options:
vlm-1,
vlm-1:auto,
vlm-1:fast,
vlm-1:pro
domain

The domain identifier for the model (e.g. video.transcription). Optional when a skill is provided via config.skills.

Available options:
video.transcription,
video.transcription-summary,
video.summary
batch
boolean
default:true

Whether to process the document in batch mode (async).

Response

Successful Response