ByteDance

OmniHuman: AI avatar video

ByteDance OmniHuman avatar generation.

Video is paid per clip from your wallet, no subscription. The studio shows the price before you pay, and top ups start at $5.

Try OmniHuman Browse all models

Key features

OmniHuman renders at 720p. OmniHuman is built by ByteDance. On Enhance AI it runs on the same account as every other model, with no separate subscription.

Resolution

OmniHuman renders at 720p. There is no resolution picker for this model, so every render comes back at the same size. For a bigger frame, run the finished clip through a video upscaler on the same account.

Input modes

OmniHuman takes an image and an audio file. Add them in the studio, check the preview and render. Every output lands in your history, ready to download or to pass to another model on the same account.

Specifications

Provider: ByteDance
Type: Video
Resolution: 720p

How to use OmniHuman on Enhance AI

1
Sign in and pick OmniHuman
Open the Video Studio on Enhance AI and choose OmniHuman from the model list. Video is paid per clip from your wallet, which starts empty on a new account, so top it up before your first render. The Try button on this page opens the studio with OmniHuman already selected.
2
Add your files
Upload an image and an audio file in the studio, then check the preview before you render. A well lit portrait facing the camera and a clean voice recording give the most natural result; a busy background or a side profile gives less.
3
Generate, then download
Press Generate. OmniHuman renders in the cloud and the clip lands in your history on Enhance AI, where you can download the MP4. You see the price before you confirm.

What people make with OmniHuman

Presenter videos

Give OmniHuman a portrait and a voice and it returns a presenter delivering the lines, with natural head movement and expression. Product updates, welcome messages and announcements can be produced from a script and a photo, and rerecorded by changing the audio rather than the shoot.

Course and training clips

Training content dates quickly and reshoots are expensive. With OmniHuman the presenter is a portrait and a recording, so a changed policy or a new screen means a new audio file and a rerender, not a studio day. Every lesson keeps the same face and the same tone.

Customer updates and support

Short spoken updates land better than a wall of text. OmniHuman turns a written message read by a voice into a clip of a person saying it, which is how a small team can put a face on release notes, onboarding and support answers without a camera or a crew.

Common questions

What is OmniHuman?: OmniHuman is an avatar video model from ByteDance. It takes an image and an audio file and returns a finished clip. On Enhance AI it runs on the same account as all the other top models, with no separate subscription.
What do I need to upload to use OmniHuman?: An image and an audio file. Add them in the studio on Enhance AI, check the preview and render. The output lands in your history, ready to download or to pass to another model on the same account.
What resolution does OmniHuman output?: OmniHuman renders at 720p.
Is OmniHuman free to try?: No. Video on Enhance AI is paid per clip from your wallet, and a new account starts with an empty wallet, so there are no free OmniHuman clips. The free tokens you get on signup, with no card needed, pay for image and audio tools, not video. Wallet top ups start at $5.
What does it cost to run OmniHuman?: OmniHuman renders are billed from your wallet by the length of the file you upload. You see the price for your settings before you render.
Do I need a separate subscription for OmniHuman?: No. OmniHuman runs on the same Enhance AI account as every other model, so you are not paying one provider for video and another for images.