Skip to content

AI video generator, with sound

Describe a shot, or start from an image, and render it with 7 video models from Google, OpenAI, Kuaishou, ByteDance and Alibaba.

From 5 credits per clip
Cinematic film still of a lone astronaut walking through a field of tall sunflowers at golden hour, anamorphic lens flare, 35mmVideo

Slow dolly in on a lone astronaut walking through tall sunflowers at golden hour, petals drifting, wind and distant birdsong

Veo 3.1 Fast8s1080pAudio

How it works

  1. Write the shot

    Subject, action, camera and sound. Or attach a start frame, and an end frame where the model supports it.

  2. Pick model, length and format

    Choose the model, seconds, resolution, aspect ratio and audio. The price updates as you change them.

  3. Keep working while it renders

    Clips render in the background and the activity tray tells you when they're ready, on any page.

More about Video Studio

Describe a shot, or start from an image, and render it with 7 video models from Google, OpenAI, Kuaishou, ByteDance and Alibaba. Most of them generate audio with the picture.

What you get

Native audio
Dialogue, effects and ambience generated with the picture on Veo 3.1 Fast, Veo 3.1, Kling 3.0, Seedance 2.5, Sora 2 and Veo 3.1 Lite.
Up to 15 seconds
Kling 3.0 and Seedance 2.5 render 15-second shots; Veo renders 4 to 8 seconds.
Start and end frames
Every model can start from an image; Veo 3.1 Fast, Veo 3.1, Kling 3.0, Seedance 2.5 and Veo 3.1 Lite can also land on an end frame.
Vertical, wide and square
9:16 for Reels and Shorts, 16:9 for YouTube, 1:1 and more depending on the model.
Camera moves
Dolly, orbit, pan, crane and handheld presets added to the prompt for you.
Refunds on failure
If a render fails, its credits come back automatically.

Models

Open one for its settings, limits and prices.
Models for ai video generator, with sound
ModelFrom
Veo 3.1 FastGoogleVeo 3.1 quality with faster turnaround and a lower price, with audio.16per clip
Veo 3.1BestGoogleGoogle's flagship video model, with the highest fidelity and native audio.32per clip
Kling 3.0KuaishouCinematic motion up to 15 seconds, with optional native audio.34per clip
Seedance 2.5NewByteDanceByteDance's newest video model, with synced dialogue, sound and long shots.21per clip
Sora 2OpenAIOpenAI's video model, with synced audio in every clip.16per clip
Veo 3.1 LiteBudgetGoogleThe budget Veo, with native audio built in. Great for drafts and social clips.8per clip
Wan 3.0BudgetAlibabaLow-cost cinematic video up to 1080p, without audio.5per clip

Questions

Something else? Ask us and a person will answer.

What is the best AI video generator?

Veo 3.1 for the highest fidelity with sound, Kling 3.0 for longer 15-second shots, Seedance 2.5 for dialogue, Sora 2 for short narrative clips with audio and Wan 3.0 for low-cost silent b-roll.

Can I make a video from text only?

Yes. Every video model works from a prompt alone. Adding a start frame gives you more control over the look.

How long does a video take to render?

Usually one to three minutes depending on the model and length. You can keep working while it renders.

How much does an AI video cost?

From 5 credits for a short silent draft. The default Veo 3.1 Fast clip (8 seconds, 1080p, with audio) is 48 credits. Plans start at $10 a month for 100 credits ($8 a month billed yearly), and the exact cost of every generation shows on the Generate button before you run it. Failed generations are refunded automatically.

Can I use the results commercially?

Commercial use is included on the Pro and Business plans. See the Terms of Service for the details of the license.