Avatar
ST
SadTalker
Fast and affordable talking head generation from a single photo. Good for testing and quick iterations. Expression control available.
Try SadTalker
Generating withSadTalker8c per generation
Created with SadTalker
Studio portrait of a 55-year-old Brazilian woman with silver
Studio portrait of a friendly woman in her 30s with curly da
Features
- Fast Generation
- Expression Control
- Budget Friendly
- Single Photo Input
Specifications
- Resolution
- 256x256 to 512x512
- Input
- Photo + Audio
- Audio Limit
- 30s
- Output
- MP4 Video
Input Requirements
Portrait Photo*
Image upload
Front-facing portrait photo
Audio File*
Audio upload
Speech audio (max 30s)
Expression Scale(optional)
Range
Still Mode (head only)(optional)
Toggle
Preprocess(optional)
Choice
Related Models
OmniHuman v1.5
Photo + Audio to talking avatar
from 3 credits · $0.30-$7.20
Kling Avatar v2
Versatile lip sync for any character
from 2 credits · $0.20-$10.40
Sync-3 Lipsync
Video dubbing with 4K lip sync
from 3 credits · $0.30-$12.10
Hunyuan Avatar
Talking and singing (Deprecated)
Fabric 1.0
Photo + audio talking avatar
from 2 credits · $0.20-$13.50
Infini Talk
Audio-driven talking avatar
from 5 credits · $0.50-$16.80
Wan 2.2 S2V
Speech-to-video from photo + audio
from 4 credits · $0.40-$2.30
Frequently Asked Questions
How much does SadTalker cost?
SadTalker costs 8 credits per generation (~$0.80). You get 10 free credits every day to try it.
Can I use SadTalker outputs commercially?
Yes, all content generated with SadTalker on Arteza comes with a commercial license.
What file format does SadTalker output?
MP4 video files with lip-synced audio.