omnihuman2

AI Character Animation Generator

Upload an illustration, clay figure or mascot and an audio track. The character speaks or sings it, with facial expression and body movement that follow the voice.

Input: Drawn or clay character image + voice · Output: MP4, 4–120 seconds

Sample: Mascots & characters · Drawn or clay character + voice. Generated with OmniHuman 2.

How it works

  1. Step 1

    Upload your character image, or describe one in text and generate it as a portrait.

  2. Step 2

    Add a voice: your own recording, an actor's take, or a generated voice from text.

  3. Step 3

    Generate and download an MP4 of your character performing the audio.

Why use it

Not just realistic people

Works with drawn, clay and stylised characters, not only photographs.

No rigging or keyframes

Skip the animation software. One image and one audio file are the whole input.

Expression follows the voice

Tone and emotion in the audio influence how the character moves.

Fast iteration

Test a character voice in seconds of video, then refine. Each video is 4 to 120 seconds long.

Example direction prompts

Optional text you can add in the studio to guide the scene, movement and camera.

Frequently asked questions

Is this full 2D or 3D animation?

No. It animates a single character image to match an audio track. It is well suited to talking mascots and short character clips, not full multi-scene animated films.

Which character styles work?

Illustrations, clay figures and stylised mascots with a clearly visible face work best. Results vary by style, so test a short clip first.

Can I create the character from text?

Yes. The studio can generate a portrait from a text prompt for 1 credit, which you can then animate.

Can I use copyrighted cartoon characters?

Only if you have the rights. Use your own characters or ones you are licensed to use.

How long can the animation be?

Each video is 4 to 120 seconds long. For longer pieces, create several clips and edit them together.

Make your first video

Plans start at $9.99/month. 1 credit = 1 second of video, and failed generations are refunded.

More use cases