Turning Text into Multi-Voice Audiobooks with Gemini

Ever wondered how to turn plain text into an engaging, character-driven audiobook — automatically? In this session we’ll build a real-world pipeline that uses Gemini to analyze a story, detect who’s speaking, and assign fitting synthetic voices to each character. You’ll see how to orchestrate multiple text-to-speech engines, handle dialogue attribution, and manage seamless voice transitions to create a natural listening experience. Expect live demos, practical tips, and a behind-the-scenes look at how AI can become an audiobook director — from raw text to a lively, multi-voice performance.