A multimodal AI understands or creates several kinds of content, for example text, images, speech and video.
Illustration: AI-generated · AI Compare Ninja · CC BY 4.0
Example
You take a photo of a menu and the AI translates it and explains the dishes.
For pros
Multimodal models map images, audio and text into a shared representation. Which inputs and outputs a model supports is listed in the vendor’s documentation.
