Veo 3
AI Model
Video
Current
Video with native audio — dialogue, effects and all.
You're looking at an AI model record: who built it, what it can do, and the hardware and data behind it.
Veo 3 (May 2025) generated synchronized speech, sound effects and music with its video — the first mainstream model to ship sound-on generation — and spread through Gemini, YouTube Shorts and advertising workflows, with Veo 3.1 refining control in October 2025.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Developed by
Competes with
Sources
Record reviewed as of 2026-01-15 — see Methodology.