Google Cloud Next '26• Apr 23, 2026• 19:22ConferencePanel

Nano Banana, Veo, and Lyria: Mastering the Google gen media stack

From Google Cloud Next '26 · 2026

Khulan Davaajav•Product Marketing Manager, Gen Media, Google

Executive Summary

Google is consolidating its creative AI tools under the 'Generative Media Models' umbrella, including Nano Banana (image), Vio (video), Lyria (music), and Gemini Audio (speech/transcription).
The models are designed for a multi-modal workflow, where Gemini can analyze video frames to generate timestamped prompts for music (Lyria) or analyze images to create detailed artistic prompts for image generation (Nano Banana).
Google announced Gemini 3 Flash Live with a 'Live Avatar' feature, enabling real-time, audio-to-audio conversational AI that can connect to Google Search for live data.
The future of creative AI is focused on 'world models' like Google's Journey 3, which will allow creators to operate within a generated environment, and on reducing generation latency to maintain creative flow.

12 quotes

Concerns Raised

High latency in asset generation can break a creator's 'flow state', disrupting the creative process.

Opportunities Identified

Leveraging the full suite of Generative Media Models to enable a single person to execute a complex, multi-modal creative project.
Developing new applications in education, customer service, and entertainment using the real-time, data-connected Live Avatar feature.
The future potential of 'world models' to create fully immersive and interactive generated environments.

Key Themes

Integrated Multi-modal AI Workflow

The presentation demonstrates a complete creative pipeline using a suite of interconnected AI models. An initial idea is storyboarded with Gemini, images are created with Nano Banana, animated with Vio, scored with Lyria, and given a voiceover with Gemini Audio, showcasing a seamless, end-to-end content creation process.

This highlights the shift from single-purpose generative tools to integrated ecosystems, enabling a single creator to produce complex, high-quality media without needing a large team or multiple disparate software tools.

Granular Creative Control

Google's new models emphasize fine-grained control for creators. Nano Banana accepts prompts specifying camera lenses and lighting, Lyria can sync musical changes to specific timestamps, and Gemini Audio's text-to-speech uses ~200 tags to control emotional expression and delivery.

This level of control addresses a key limitation of early generative AI, moving beyond generic outputs to allow professional creatives to implement a precise artistic vision and style.

AI-Assisted Prompt Engineering

A key technique shown is using one AI to help prompt another. The speaker uses the Gemini app to analyze inspirational images and videos, which then generates the detailed, technical prompts needed to achieve a specific style in the Nano Banana image model or a synchronized score in the Lyria music model.

This meta-use of AI lowers the barrier to entry for complex prompt creation, allowing users without deep technical knowledge of photography or music theory to achieve professional-level results by leveraging the AI's contextual understanding.

Real-Time Conversational AI

The launch of Gemini 3 Flash Live with its Live Avatar feature marks a move towards interactive, real-time AI. The demo showcases an avatar that can hold a conversation, understand context, and pull live data from Google Search, all powered by a low-latency audio-to-audio architecture.

This technology opens up new application categories beyond static content generation, such as interactive educational tutors, dynamic customer service agents, and live-streaming virtual characters.

The Future of Immersive Creation

The speaker looks ahead to 'world models' like Google's Journey 3 as the next frontier. These models will create entire interactive environments, shifting the creator's role from generating static assets to being a 'camera operator' within a dynamic, AI-generated world.

This signals a long-term vision for generative AI that moves beyond 2D media into creating fully immersive, explorable digital spaces, with significant implications for gaming, simulation, and virtual reality.

Get started free

Topics

Generative Media Models Multi-modal AI Creative AI AI Workflow Nano Banana Vio 3.1 Lite Lyria 3 Pro Gemini Audio Gemini 3.1 Flash Gemini 3 Flash Live Live Avatar World Models Journey 3 Prompt Engineering Text-to-Speech (TTS)Video Generation Music Generation Image Generation

Processed Apr 28, 2026 yt-dlp + mlx-whisper + Gemini