OmniHuman v1.5
Create hyper-realistic talking avatars from a single portrait photo and audio file. Features perfect lip sync, natural facial expressions, and gesture generation synchronized to speech rhythm and emotion.
Try OmniHuman v1.5
Created with OmniHuman v1.5
Studio portrait of a 40-year-old Japanese woman with silver-
Welcome to Arteza. Every image, video, and sound on this pag
Studio portrait of a friendly woman in her 30s with curly da
Studio portrait of a friendly woman in her 30s with curly da
Studio portrait of a young man with short locs and a denim j
Studio portrait of a man in his 40s with short grey beard an
Features
- Single Photo Input
- Perfect Lip Sync
- Natural Expressions
- Gesture Generation
- Turbo Mode
- 720p/1080p Output
Specifications
- Resolution
- 720p or 1080p
- Input
- Portrait photo + Audio file
- Audio Limit
- 60s at 720p / 30s at 1080p
- Output
- MP4 Video
Input Requirements
Related Models
Kling Avatar v2
Versatile lip sync for any character
SadTalker
Budget avatar from photo + audio
Sync-3 Lipsync
Video dubbing with 4K lip sync
Hunyuan Avatar
Talking and singing (Deprecated)
Fabric 1.0
Photo + audio talking avatar
Infini Talk
Audio-driven talking avatar
Wan 2.2 S2V
Speech-to-video from photo + audio
Frequently Asked Questions
How much does OmniHuman v1.5 cost?
OmniHuman v1.5 costs 3 credits per generation (~$0.30-$7.20). You get 10 free credits every day to try it.
Can I use OmniHuman v1.5 outputs commercially?
Yes, all content generated with OmniHuman v1.5 on Arteza comes with a commercial license.
What file format does OmniHuman v1.5 output?
MP4 video files with lip-synced audio.