Chapter 22: Multimodal Voice AI — When Voice Is One Channel Among Many

Voice and AI, Chapter 22: how voice behaves when combined with text, visuals, touch, and context — shared representations, audio tokens, output choreography, and why multimodality reshapes design thinking.

2026-06-03 Last updated on: 2026-06-03 Sho Shimoda

voice ai multimodal shared representations audio tokens agents interaction design Voice and AI book

Back to Voice and AI