Build creative apps with the GenMedia suite
summary
Shows how the GenMedia suite (Nano Banana, Veo/Omni, Lyria, Gemini Flash TTS) is used end-to-end to turn a Project Gutenberg book into character portraits generated with Nano Banana, 3 illustrated chapters and short videos via Veo, music tracks from Lyria and dual-voice TTS clips stitched together. Demonstrates the Interactions API stateful workflow, clients.file.upload for large texts, service-tier priority and retry options, a three-chapter pipeline that keeps character consistency, and Omni’s selective video edits with basic physics-aware motion.
AI-written summary · about
chapters (12)
- 0:00GenMedia introduction
- 2:33Setting up the workshop environment
- 4:44Uploading book with file API
- 6:30Multimodal workflows
- 7:54Character illustrations with Nano Banana
- 10:06Chapter illustrations
- 13:03Images to videos with Veo
- 15:08Chapter music with Lyria
- 17:45Text to speech for narration
- 20:36Combining media
- 22:40Omni for video editing
- 26:17Conclusion and key takeaways
related talks
01h 17mLet's go Bananas with GenMedia
01h 55mPrompt to Pipeline: Building with Google's Gen Media Stack
01h 03mBuild & deploy AI-powered apps
16mAny-to-Any: Building Native Multimodal Agents
20mDesign for the future of apps
33mNew Renaissance of Building
56mBuilding Multimodal Apps with Gemini 2 0 and Gemini SDK
10mBooks reimagined: AI to create new experiences for things you know