MODEL LINEAGE
中文
Model index
Google DeepMind·Veo / Gemini Video

Veo 3

Added native dialogue, ambience, and sound effects to Veo.

LegacyVideo generationMultimodalWeights not released
MODEL NUMBER160
Release date
2025-05-20
Organization
Google DeepMind
Family
Veo / Gemini Video
01

Specifications

Only published specifications are shown.

Input modalities
Text · Image
Output modalities
Video · Audio
Open weights
No
Status
Legacy
02

Overview

Overview

Added native dialogue, ambience, and sound effects to Veo.

03

Changes from predecessor

Compared with Veo 2 ↗

PreviousVeo 2— · — ctx
CurrentVeo 3— · — ctx
New capabilities Native audio Dialogue generation
04

Architecture & capabilities

Key capabilities

Native audioDialogue generationVideo generation
05

Release history

General release

Veo 3 added native audio.

View source
06

Related models

Select a card to view the related model.

PredecessorVeo 2View details →SuccessorsVeo 3.1View details →
07

Sources

01
Introducing Veo 3 and Imagen 4Google · 2025-05-20
Official · Verified