Skip to content

AI 101

Multimodal

Sketch: one mailbox with four slots, for text, an image, audio and video; a letter goes into the text slot.

A multimodal model can take in or produce more than one kind of data, such as text, images, audio or video.

Think of it like this: It is an engine that runs on several kinds of fuel.

Source:

https://developers.google.com/machine-learning/glossary#multimodal-model (checked Oct 15, 2026)

RelatedLLMTypes of AI modelsImage modelSpeech-to-text

Used inImage model LLM Robotics model Speech-to-text Text-to-speech Types of AI models

— Cases4AI, powered by AIRVX