Multimodal Capabilities
Multimodal capabilities allow VAs to combine use inputs via text, voice and touch (on a screen) with ability to process data from various data sources beyond just text, like images, video, tables, maps, etc.
Multimodal capabilities allow VAs to combine use inputs via text, voice and touch (on a screen) with ability to process data from various data sources beyond just text, like images, video, tables, maps, etc.