Loading
Work with images, audio and documents, not just text.
Starting with What multimodal models do, Vision models, Sending images to a model, Speech, Speech-to-text, Multimodal RAG, and more
Made for you now: slide lessons from basics to production, usually with code and a quiz. See a finished one
Work with images, audio and documents, not just text.
AI EngineeringStage 15 of 17: Multimodal
Start with these 6. 9 more are one tap away.
One model that takes text, images, audio or video as input.
Read screenshots, charts and photos.
Formats, sizes and the token cost of images.
Speech-to-text and text-to-speech in apps.
Transcribe audio with Whisper-style models.
Search and answer over images, slides and diagrams, not just text.