Filmmakers and marketers wanting video with sound from Google; at $0.40 a second via the API, clips get expensive quickly.

Kenning's take

What it does

Veo 3.1 is Google's video generation model, building on Veo 3 with richer generated audio, closer prompt following and more realistic textures. In Google's Flow filmmaking tool it powers features that use reference images, first and last frames, and clip extension, all with sound. It is also available in the Gemini app, through the Gemini API and on Vertex AI.

• Video with generated audio
• Ingredients to Video using reference images
• Frames to Video from a start and end image
• Extend clips to a minute or more
• Fast and Lite variants on the Gemini API

Who it suits. Filmmakers, marketers and developers who generate short video clips from text or images.

Key facts

Category

AI models

Part of

Google Flow

Made by

Google DeepMind

Released

15 October 2025

How to get it

in Flow and the Gemini app, through the Gemini API (paid tier) and Vertex AI

Works on

Web, iPhone, Android, API

API price

Veo 3.1 $0.40 per second (720p/1080p), $0.60 per second (4K); Veo 3.1 Fast from $0.10 per second

FAQ

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.