Generates embeddings for text in the same latent space as video, so that it is possible to perform text-to-video searches by embedding the text and comparing it to the video embeddings.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The text to embed. Max length 300 characters
"People walking on the street"
Successful Response
The embedding of the text, a list of 512 floats