Search options

Search options specify the source of information the video understanding model uses when performing a search. The following values are supported:

• visual: Analyzes video content as you would see it, including actions, objects, events, text (OCR) and brand logos.
• audio: Analyzes video content as you would hear from it, including ambient sounds and human speech.

📘

Notes

• The search options you specify must be a subset of the model options used when you created the index.
• You can specify multiple search options in conjunction with the operator parameter to broaden or narrow your search. For examples, see the Visual and audio section of the Text queries page.