Video · by ByteDance (BytePlus)

OmniHuman

Turn one photo and audio into a full-body singing video.

image, speech, music, text → video · image, speech → video
Way in
Official APISign up yourself, api key
To start
$
Runs
In the cloudAlso through fal, hedra, Replicate
Checked
Nov 3, 2026Prices as of that day

What it can do 2

Generate a full-body talking or singing performance from one image and an audio track30-300 s output (BytePlus); 720pimage, speech, music, text → video$0.07/s (BytePlus official, OmniHuman 2.0); $0.105/s on fal/Hedra; v1.5 $0.16/s
Lip-sync-only avatar variantimage, speech → video$0.12/s (BytePlus)
Prices and limits as of Nov 3, 2026, from ByteDance (BytePlus)’s own pages. They change; check before you rely on them.Not affiliated with ByteDance (BytePlus). Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.