Veo 3 for Developers — Paige Bailey, Google DeepMind

4.8K views · Jun 21, 2025 · 20:37 min · Watch on YouTube ↗

Takeaway

Veo 3 + Imagen 4 + Lyria 2 collapse video, image and music generation into one developer-accessible stack with native multimodal control and SynthID safeguards.

Summary

Veo 3 generates video and audio natively with composed tokens across modalities — not audio bolted on as a tool — built on GQN/Walt research lineage
Veo 2 features available via API and Flow: reference-powered video, outpainting, add/remove objects, character control + consistency, first/last-frame interpolation
Human raters preferred Veo over Runway Gen-4 and Kling on side-by-side reference-powered video benchmarks
Imagen 4 handles realistic image generation including typography (Alamo Square/Mission stamps); Lyria 2 produces high-fidelity professional-grade music with granular creative controls
Responsible AI built in: visible watermarks and SynthID; deep collaborations with Darren Aronofsky, Jacob Collier and Toro Y Moi via Music AI Sandbox and Lyria RealTime

video-generationveomultimodal

Original description

This talk will briefly trace the history of video generation models before diving into Veo 3, Google DeepMind's latest state-of-the-art model that marks a significant leap by generating video with synchronized audio—including dialogue, sound effects, and music—all from text and image prompts. We'll show how it can understanding intricate details, maintain coherence over longer sequences, and simulate realistic physics and camera movements.

For developers, Veo 3, accessible via Vertex AI (preview), unlocks many new capabilities. We'll discuss how its advanced capabilities, such as semantic context rendering and cinematic control, can empower innovation in filmmaking, game development, education, and more. This session will cover how developers can integrate Veo 3 into their workflows, or test it out today in the Gemini App, Flow, and via the Gemini APIs on Google Cloud.

Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter