minimaxiH3 Get access

Models

Audio-to-video models.

Drive a face or a scene from speech and music: lip-sync and talking-avatar models. 3 models, priced per second, with a sample output each.

All 328Text-to-video 71Image-to-video 111Video-to-video 18Audio-to-video 3Text-to-image 60Image editing 65
ByteDance · Audio-to-video

Avatar Omni Human 1.5

OmniHuman 1.5 is ByteDance's digital-human model that turns a single portrait plus an audio track into a lifelike video …

from $0.18/sec
VEED · Audio-to-video

Veed-fabric-1.0 Image-to-Video

VEED Fabric 1.0 is a high-speed image-to-video generation model powered by VEED's Fabric technology. It transforms a sin…

from $0.13/sec
VEED · Audio-to-video

Veed-fabric-1.0-fast Image-to-Video

VEED Fabric 1.0 Fast is a high-speed image-to-video generation model powered by VEED's Fabric technology. It transforms …

from $0.17/sec

Run any of them in Chat.

Invite code opens Chat with every model above. No code? Join the waitlist and tell us which model you need.

Get access Browse models