Engine options indicate the types of information a video understanding engine will process. When creating a new index, you must specify the engines and the associated engines options that you want to enable.

The following engine options are available:

• visual: This option allows you to analyze video content as you would see and hear from it, including actions, objects, sounds, and events, and excluding human speech.
• conversation: This option allows you to analyze human speech within your videos.
• text_in_video: This option allows you to detect and extract text (OCR) shown within your videos.
• logo: This option allows you to identify the presence of brand logos within your videos.

Selecting engine options

• Marengo: When using the Marengo family of video understanding engines, specify any combination of the available engine options.
• Pegasus: When using the Pegasus family of video understanding engines, specify one or both of the following engine options: visual and conversation.

📘

Note

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