Google's Veo 3 family

Veo 3 AI video generator, now on Veo 3.1

Veo 3 made AI video talk: picture, dialogue and sound from one prompt. GetVeo3 runs its current version, Veo 3.1, in your browser, with no Gemini subscription or API key.

  • Dialogue with lip sync
  • Text or image to video
  • No Gemini subscription

Create

One optional starting image, used as the first frame (PNG, JPEG, WebP, up to 10 MB)
Model
Aspect ratio
Resolution
Length

960 credits

Your videos

Your next shot plays here

Describe a shot and its sound, choose a model and length, then generate. New videos appear here and stay in your history.

Start from an idea

At a glance

Veo 3 is Google's AI video model that generates video and native audio together from a text prompt or an image. Google announced it at Google I/O in May 2025 and updated it to Veo 3.1 in October 2025. On GetVeo3 the Veo 3 family runs as Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite: 4 to 8 second clips in 16:9 or 9:16 at 720p, or 1080p for 8-second clips, from 15 credits per second with purchased credits.

Developer
Google DeepMind
Released
Veo 3 in May 2025; Veo 3.1 in October 2025
Models here
Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite
Price per second
120 credits with Veo 3.1, 30 with Veo 3.1 Fast, 15 with Veo 3.1 Lite
Length and size
4, 6 or 8 seconds at 720p, or 8 seconds at 1080p; 16:9 or 9:16
Sound
Native audio generated with the picture: dialogue, effects, ambience

What Veo 3 changed for AI video

  • 01

    Sound in the same pass

    Veo 3 was Google's first Veo model to generate audio with the video: voices, effects and ambience in sync with the action.

  • 02

    Characters who speak

    Write a line of dialogue in quotes and the speaker delivers it with matching mouth movement.

  • 03

    Realistic physics

    Water, fabric, hair, crowds and vehicles move with convincing weight and timing.

  • 04

    Prompt adherence

    Detailed instructions about camera, lens, light and timing are followed closely, more so in Veo 3.1.

How to make a Veo 3 AI video

  1. 01

    Describe the scene and sound

    Subject, action, setting and camera, then the sounds and any dialogue in quotes.

  2. 02

    Choose a Veo 3.1 model

    Veo 3.1 for final quality; Fast at 30 or Lite at 15 credits per second for drafts.

  3. 03

    Set shape and length

    16:9 or 9:16; 4, 6 or 8 seconds at 720p, or 8 seconds at 1080p. The price updates before you generate.

  4. 04

    Generate and download

    Download the MP4 with sound, or reuse the settings to refine the prompt.

Veo 3 vs Veo 3.1

Veo 3.1 is the October 2025 update to Veo 3, not a separate product line. Google introduced it with richer native audio, closer prompt adherence and more control when generating from images, and released Veo 3.1 Fast alongside it.

GetVeo3 runs only the 3.1 versions, so a Veo 3 prompt you find online works here as written. When people say Veo 3 video generator today, Veo 3.1 is the model they get.

Gemini Veo 3 or a Veo 3 video generator site?

Google offers Veo in the Gemini app and in Flow, its filmmaking tool, generally as part of its Google AI plans, and to developers through the Gemini API and Vertex AI. Those are good choices if you already pay for them.

GetVeo3 is for people who want Veo by the clip: no subscription is required, every model and length shows its credit price first, and one-time packs start at $9.99. Your videos stay in your history on any device you sign in from.

What Veo 3 is good at

Veo 3 clips are short, so they work best as single shots that you cut together:

  • Short dialogue scenes: one or two lines, one or two speakers
  • Cinematic b-roll with real ambience: cities, nature, interiors
  • Product and food shots with tactile sound
  • Vertical 9:16 clips for TikTok, Reels and Shorts
  • Animating a still image, such as a portrait, illustration or render

Limits worth knowing

Each clip is 4, 6 or 8 seconds, so plan one shot per prompt and edit longer stories together. Small on-screen text, hands and fast action with several people can still come out wrong; simplify the shot or regenerate. Google's safety filters block some prompts and images, such as requests involving real public figures; blocked jobs are refunded. 1080p is available only for 8-second clips; 4 and 6 second clips render at 720p.

Veo 3 models on GetVeo3

Prompts, audio, lengths and resolutions are the same on all three models; quality and price per second differ.

Veo 3.1Veo 3.1 FastVeo 3.1 Lite
Credits per second1203015
8-second clip960 credits240 credits120 credits
8 seconds in dollars$8.00–$9.60$2.00–$2.40$1.00–$1.20
Best forFinal shotsDrafts, socialTests, volume

Veo 3 FAQ

What is Veo 3?

Veo 3 is Google's AI video generation model that creates video and native audio together from text or an image. It was announced at Google I/O in May 2025; Veo 3.1, released in October 2025, is its current version.

Is Veo 3 the same as Gemini Veo 3?

Yes, it is the same model family. In the Gemini app, Veo is one of Gemini's tools; GetVeo3 runs Veo 3.1 directly through a model API, without a Gemini subscription.

Can I still use the original Veo 3?

GetVeo3 runs the 3.1 versions only: Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite. They accept the same prompts as Veo 3, with richer audio and closer prompt adherence.

Is the Veo 3 AI video generator free here?

No. Every clip uses purchased credits, and new accounts receive no free credits. The lowest-cost option is Veo 3.1 Lite: 120 credits for an 8-second clip.

Can Veo 3 speak languages other than English?

Yes, Veo can deliver lines in other languages, but English is the most reliable. Keep other-language lines short and test them with Veo 3.1 Lite first.

How long does a Veo 3 video take to generate?

Most clips are ready in one to three minutes; busy periods can take longer. You can leave the page, and the video appears in your history when it is done.

Make a Veo 3 video with sound

Buy credits and turn a scene and a line of dialogue into a clip.

Last updated October 6, 2026

Create your account