Hotel Lobby AI turns two portrait photos into a template-based rap duet performed on an orange studio stage. Upload one photo for the left performer and one for the right — each a single person with a clear, evenly lit face — optionally add a one-sentence direction for a gesture or expression, and the tool generates a roughly ten-second duet clip following the reference performance, complete with the template soundtrack. Output comes in 480p, 720p, or 1080p, in vertical 9:16 or landscape 16:9, downloadable as an MP4 for greetings, social clips, and trend posts. The format is deliberately narrow: this is not a timeline editor or a general video generator, but a focused two-photo duet maker with the choreography, cuts, and staging already decided. Pricing is per video with no subscription — $3.90 at 480p, $6.90 at 720p, and $9.90 at 1080p — unused passes never expire, and a confirmed generation or sound failure returns the allowance at the same quality. Photos and results are private by default, and the site is clear-eyed about likeness: faces and lip sync can vary, and template previews show the reference performance rather than promising your exact result.