BasicsEasy read
Multimodal
Written by Minh Khang
What is Multimodal?
Multimodal AI is AI that takes in and gives back several kinds of content at once: text, images, voice and video.
A multimodal model can look at a photo a customer sends and answer in text, or listen to a voice note and summarise it. Being able to see is not the same as seeing right: small details and blurry text are still easy to misread.
Multimodal in a shop
A customer sends a photo of a torn seam; the AI describes the fault and suggests an exchange, and staff only check and approve.
Keep learning beyond the glossary
Read next
- BasicsLarge language model (LLM)A large language model (LLM) is the text brain behind ChatGPT, Gemini and Claude: it predicts the most likely next word, one word at a time.
- Risks and safetyDeepfakeA deepfake is a fake image, voice or video made by AI that looks like a real person or event, often hard to tell apart.