AI rap video generator that turns your selfie into a short vertical rap video
Generate AI videos of you and your friends performing the viral Outstanding Tiny Desk concert
Stage
Not given
Startup
Founded
Not given
2026
Based in
US
Not given
Pricing model
Paid
Paid
Pricing
Not given
Single Video: $9.99 for 1 video (1–5 people); Party Pack: $19.99 for 3 videos ($6.66 per video); Five Pack: $29.99 for 5 videos ($6.00 per video). All are one-time purchases with credits that never expire. Failed renders return credits automatically. Unused credits can be refunded within 14 days of
Key features
Choose from templates (rap booth, dance, duo, funny, Chinese style scenes)
Select from original music library with licensed songs
AI face insertion with automatic lip-sync
Vertical 720×1280 video format for social platforms
Free photo quality check before video generation
One free remake within 7 days
Removable AI watermark
AI-generated label in metadata
No sign-up required, guest checkout with email only
Video available on order page for 30 days
Upload 1–5 photos and assign to five roles: lead vocals, keyboard, back-left vocals, back-right vocals, saxophone
AI fills in clothing not shown in photos
Renders approximately 18-second 720p video at 9:16 aspect ratio
Download video with song and silent copy
Rendering typically takes 5–10 minutes
Photos deleted automatically after 30 days
Failed renders automatically return credits
Payment options: card, Apple Pay, Google Pay
What makes it different
Template-based system with viewable samples before purchase, eliminating guesswork
Pay-per-video with no subscription or free trial required
Automatic refund after 3 failed video attempts
Original licensed music library, not covers of famous songs
Photos deleted within 7 days, videos after 30 days for privacy
No subscription; one-time purchase per video with credits that never expire
One video price covers 1–5 people, not multiple videos
Independent fan tool not affiliated with NPR, Charlie Wilson or The Gap Band
Photos used only for video generation, not for model training