Video -> JSON
Generate structured prediction for the given video file.
Try our Colab Cookbook Example
Try our Colab Cookbook example for long-form video transcription.
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
Request to the Video API (i.e. structured prediction).
The domain identifier for the model (e.g. video.transcription
).
video.transcription
, video.transcription-summary
, video.tv-news-summary
, video.dashcam
Optional metadata to pass to the model.
The VLM generation config to be used for /<dtype>/generate.
The URL of the file (provide either file_id
or url
).
The ID of the uploaded file (provide either file_id
or url
).
Unique identifier of the request.
Date and time when the request was created (in UTC timezone)
The URL to call when the request is completed.
1
The model to use for generating the response.
"vlm-1"
Whether to process the document in batch mode (async).
Response
The response is of type any
.