Veo 3.1 Launch Recap: Native Audio Becomes the Standard
The flagship feature
Native dialogue + ambient sound in one render. No more triple-pass (visual → voice → mix).
Full feature list
- 10-second 1080p clips.
- Native English dialogue (lip-synced, sub-4s lines best).
- Native ambient SFX (footsteps, wind, traffic, room tone).
- Image-to-video robust (GA from beta).
- Native 9:16 + 16:9 + 1:1.
- 4K upscale path.
Pricing
~$0.75/second on Google AI Studio. Mid-tier among premium models.
Impact on the market
Every other premium model now has to ship native audio or lose share. Expect Kling, Runway, and Hailuo to follow within 2 quarters.