Model options

Model options indicate the types of information a video understanding model processes. When creating an index, you must specify the video understanding models and the associated model options you want to enable. The following model options are available:

• 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, music, and human speech.

📘

Note

The search options you use when performing a search must be a subset of the model options specified when the index was created.