Create a 15-second AI video of two people performing in the orange booth, lip-synced to the original Hotel Lobby audio
AI image generator and editor on an infinite canvas for creating, editing, and expanding images
Stage
Startup
Not given
Founded
Not given
Not given
Based in
Not given
NO
Pricing model
Paid
Free trial
Pricing
$9.99 for 1 video, $19.99 for 3 videos ($6.66 each), $29.99 for 5 videos ($6.00 each). No subscription; credits never expire. Free retry if a video fails.
Free trial for 7 days. Starter plan $20/mo with 1,000 tokens monthly. Pro plan $60/mo with 3,000 tokens monthly. Studio plan $200/mo with 10,000 tokens monthly. Unlimited plan available at custom pricing. 50% discount when paying annually.
Key features
Generate 15-second videos with original Hotel Lobby audio
Vertical (720×1280) or horizontal (1280×720) format options
No account required, pay with email only
Rendering in 6-8 minutes
Support for people and pets in the booth
Free automatic retry if video fails
Clean MP4 with no watermark or logo
Videos stored for 30 days in My videos
Credits never expire
Halloween booth variant available
Inpainting to mask and regenerate image regions
Outpainting to extend images in any direction without boundaries
Instruction edits to describe changes in plain words
Multi-image input and compositing from reference images
AI agent for bulk creation and autonomous asset generation
Non-destructive editing with layers and reversible changes
Drawing, text, and shape tools on canvas
Runs in browser and installs as app on mobile and desktop
Remove background in a single step
What makes it different
Lip-syncing automatically matches faces to original audio
Pay-per-video model with no subscription or recurring charges
No editing required; videos are ready to post immediately
Works with any two people or pets, not limited to celebrities
Non-destructive infinite canvas with full professional editing capabilities
Integrated AI agent that works autonomously on the canvas to generate and compose full layouts
Works across all devices without installation directly in browser
Multiple reference images as context for precise AI-guided edits
10+ integrated high-performance AI models in one workspace