"Multimodal interfaces support user input and processing of more than one modality with a system that incorporates two or more combined user input modes such as speech, manual gestures, and touch in a coordinated manner with multimedia systems. Multimodal interfaces promise to allow users to enter information and queries through multiple input modes such as mouse and keyboard, speech, or handwriting. They coordinate natural input modalities with multimedia output modalities such as video, audio, information visualizations, 3D graphics, etc.
Multimodal interfaces help automate steps in the automation process through on-site configuration using Windows control, image-based configuration and Web control without docking the application. Every step captured via multimodal configuration is traceable."