Back to Nodes
Omni Human

Omni Human

Official

Animate a human image from an audio track.

Nodespell AI
AI / Video / Bytedance

Animate a human image from an audio track.

Omni Human is a focused image-and-audio-to-video node. Provide a person image and audio, and the output is an animated human video.

Use it when the source image defines the person and the audio drives performance. It is not a general text-to-video or scene-generation node.

Inputs (2)

Image

String

Input image containing a human subject, face or character.

Min: 0Max: 100

Audio

String

Input audio file (MP3, WAV, etc.). For the best quality outputs audio should be no longer than 15 seconds. After 15 seconds the video quality will begin to degrade. If you have a lot of audio you want to process, we recommend splitting it into 15 second chunks.

Min: 0Max: 100
Outputs (1)

Output

Inferred

Output

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Bytedance

Input

ImageAudio

Output

Video

Keywords

Video GenerationAspect ControlLength Control
Use in Workflow