What does it mean for a machine to “understand” an image? How can it generate a voice — or a video?

This volume is about the leap to multimodal AI: models that connect text, images, audio (and beyond), and then use those representations to create. The guiding theme remains the same: turning apparent magic into a mechanism you can reason about.

What you’ll learn

• Vision: from pixels to representations
• Audio: recognition, synthesis, and meaning
• Generative models: creating images/audio/video (and why it works)
• Multimodal alignment: connecting vision, audio, and language
• Accessibility: AI as a sensory bridge