# Veo 3

- Date: 2025-05
- Type: model
- Credit: Google DeepMind
- Video: https://www.youtube.com/watch?v=ODyROOW1dCo
- URL: https://aifilmhistory.org/entry/veo-3

The landmark addition: native audio generation. For the first time, a video model generates synchronized dialogue, sound effects, and ambient noise alongside the visuals in a single pass. Lip-sync accuracy under 120ms. In practice, this collapses what was previously a multi-tool workflow into a single generation. No more generating video, then finding sound effects, then syncing dialogue. The model imagines the entire audiovisual scene at once.

Links:
- Google Blog: https://blog.google/technology/ai/generative-media-models-io-2025/
- Google DeepMind: https://deepmind.google/models/veo/

---
Source: https://aifilmhistory.org/entry/veo-3
Era: 2025 · The Studio Era
Last updated: 2026-09-21