AI video generation with synced audio from reference images and text prompts
Turn 1–3 photos into 15-second Gangnam Style dance videos with zero prompts
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Paid
Pricing
Not given
Starter: $9.90 (2 credits: 1 video at 1080p or 2 videos at 720p). Five dances: $29.90 (10 credits: 5 videos at 1080p or 10 videos at 720p). Twelve dances: $59.90 (24 credits: 12 videos at 1080p or 24 videos at 720p). 1 credit = 720p HD; 2 credits = 1080p Full HD. Pay once, never expire, with zero su
Key features
Up to 9 reference images per generation
Up to 3 audio references per generation
5 fixed video lengths from 5.875 to 14.375 seconds
4 aspect ratios (16:9, 1:1, 9:16, 4:3)
24 fps frame rate
Real-time rendering for first 3 reference images
First and last frame control
MP4 output saved for 7 days
Text prompt with reference naming
Automatic credit refund for failed generations
Zero-prompt role slot mapping for 1–3 photos
5 dance templates: Street Duo, Terrace Trio, Blue Tuxedo Solo, Soccer Trio, Epic Character Trio
98.4% facial identity retention across choreography
On-device face detection and group photo auto-split
Unwatermarked MP4 export ready for social media
24-hour automatic photo deletion
What makes it different
Synced audio and video in a single generation pass
8-step distilled model for fast generation in browser
No installation or GPU required
Purpose-built for Gangnam Style choreography with no generic video AI prompts required
Multi-character identity isolation prevents face blending and morphing artifacts
Pre-synced beat-matched audio eliminates manual editing in CapCut or other tools
One-time pay-per-use pricing with no recurring subscription