Veo 3.1 enables cinematic video with synced sound from a single prompt

Make cinematic video with synced sound in Google's Veo 3.1 on Leonardo.Ai, from a prompt or a single image.

What is Veo 3.1?

Veo 3.1 and Veo 3.1 Fast, now available on Leonardo.Ai, are Google’s latest video-generation models, turning ideas into scenes from a simple text or image prompt.

Generate cinematic stories with precision and prompt control, without complex setup or specialist tools.

What you can make with Veo 3.1

High-Quality Video Output

Photorealistic motion with synchronized audio in one seamless process.

Audio Generation

Describe ambience, effects, or dialogue in your prompt, and your video comes with matching sound.

Prompt Precision

Veo 3.1 follows detailed direction on lighting, subjects, movement, and sound.

Workflow Integration

Pair with Leonardo’s suite to build moodboards, concept art, storyboards, and final video with audio.

Learn how to use Veo 3

Turn image to video with Veo 3.1

Begin with a start frame to anchor composition and tone. Then refine action, sound, and emotion via prompt for clarity and control.

Start frame

Result

New in Veo 3.1: end frames

Shape the complete story. Add an end frame to maintain continuity and control how your scene concludes.

Start frame

End frame

Result

Create more for less with Veo 3.1 Fast

Use Veo 3.1 Fast for rapid ideation and lightweight production. Draft lo-fi videos, test prompts, refine timing, and scale affordable content quickly.

A cinematic scene set at night: a glamorous woman with an afro hairstyle and gold jewellery shares a luxurious outdoor pool with a calm alligator. The pool area is surrounded by classical statues and large blue ceramic vases, all dimly lit. The camera starts at water level and slowly zooms in on the woman’s face as she makes intense eye contact with the camera. The lighting is moody and soft, with candlelight reflections on the water and a subtle fill light on her face.

Create with Veo 3.1 on Leonardo.Ai

Create cinematic video directly from your ideas.

Veo3.1VideoGenerationFAQS

How do I use Veo 3.1 on Leonardo.Ai?

Select Veo 3.1 or Veo 3.1 Fast as your video model in Leonardo, then enter a text prompt or upload an image reference and generate your video. Refine results by adjusting your prompt or using start and end frames for more control. Learn more in our guide to mastering prompts for Veo 3.

What is the token cost of using Veo 3.1 on Leonardo.Ai?

Veo 3.1 token cost scales with your video’s duration and whether audio is enabled. The exact cost for your chosen settings is shown in the generation panel before you generate.

Why use Veo 3.1 on Leonardo.Ai instead of Google’s platforms?

Leonardo combines Veo 3.1 with image and design tools in a single workflow, so you can iterate faster and get more from each generation.

What’s the difference between Veo 3.1 and Veo 3?

Veo 3.1 builds on Veo 3 with end-frame control, stronger prompt adherence, and improved synced audio. Google has retired the original Veo 3 model, so Veo 3.1 and Veo 3.1 Fast are the versions available on Leonardo.Ai.

Does Veo 3.1 generate sound?

Yes. With Veo 3.1, you can add synchronized sound to your video straight from your prompt. Check out our guide with tips for prompting for audio with Veo 3.

How do I create a start or end frame for Veo 3.1?

Upload or generate your start and end frames, then use them as anchors for your scene.

Where can I access Veo 3.1?

Veo 3.1 is available globally through Leonardo.Ai accounts.

Learn more about Veo 3.1

Guides, tutorials, and resources to help you get better results with Veo 3.1, from writing stronger prompts to creating consistent, repeatable video workflows.

Mastering prompts for Veo 3

Sometimes you have a clear vision for an image, but the AI model returns something generic or very far from what you have in mind. This is a common challenge in AI image generation, forcing many to guess at “magic words” or give up on their idea entirely.

Google Veo 3 image to video

Try prompting something simple without mentioning the style, like a handbag on a pedestal. The model will still give you something, but it’ll make assumptions. Most likely, it’ll default to photorealism or a CGI-style render, depending on what it’s seen the most in training. It won’t feel random, but it also won’t be fully yours.

Sora 2 has been retired: moving to Veo 3.1

Sora 2 is no longer available on Leonardo.Ai following a provider-side retirement. See how Veo 3.1 and Veo 3.1 Fast cover the same ground — and if you're exploring beyond the Veo family, Seedance 2.5 is our newest and most popular video model.

How to prompt audio for Veo 3 with prompt examples

These are some of the most common and important questions we hear from creators: Can I use the AI art I generate for my website? Can I use it to design T-shirts? What about for a client’s social media campaign?

Start generating

Create Professional AI Videos with Veo 3.1

From image-to-video to audio-prompted scenes, generate high-quality, consistent AI videos using Veo 3.1.