Multimodality
The ability of an AI model to process several types of data such as text, images, audio or video.
A multimodal model can, for example, describe a photo, answer questions about a chart, understand spoken language or create an image from text.
Many current chat assistants are multimodal: they accept documents, images or speech and, depending on the model, respond with text, speech or images.
General information, not legal or professional advice.