AI Music Video Generator
A music video generator made for two people — two photos, one beat, one performance.
LobbyDuo is an AI music video generator designed for duos rather than single subjects. Give it two photos and it films both faces side by side in a music-video set and has the video model perform that set’s own original 15-second rap, then hands you an MP4 with the soundtrack baked in. Six studio sets are included, and a 15-second video at Standard 2K costs 50 credits.
Built for two performers
Two-person music videos are the hard case for generative models: both faces must stay distinct, both must stay in frame, and both must perform at once. LobbyDuo is built around that constraint from the start. The prompt names a left and a right performer, the two photos are passed as separate identity references, and the model is told never to swap, merge or blend them. The camera stays locked off so neither performer can drift out of the shot, and the composition leaves room for both bodies shoulder to shoulder at a single microphone.
Six sets to film in
Every generation happens in a studio set, not against a generic background. The default is the classic orange seamless studio with a chrome condenser mic, and five more sets cover a night street corner, an orange-lit gala ballroom, a 1970s television studio, a cosy living room for pets, and a golden-hour beach with a standing mic. Sets change the backdrop, the lighting, the mood and the soundtrack, but not the price: any set costs the same credits, so switching studios is a creative decision rather than a budget one. Each set has its own sample video — with its own track — you can watch before choosing.
The soundtrack comes with it
A music video needs music, and each studio ships its own. Every set has its own original 15-second rap, written for the product, and the model films your two faces into the set and performs that rap in the same render, so the finished MP4 plays with its soundtrack wherever you post or embed it.
Credits, quality and honesty
A 15-second video at Standard 2K is 50 credits, the $9.99 pack; 5 and 10-second cuts cost 20 and 35, and the lighter 768p quality costs 10, 15 and 20. The pricing table lists what is available today. Credits are one-time and never expire. Because everything is AI-generated, results vary between runs and an exact likeness or perfect lip sync is never guaranteed; if a render is confirmed failed, your credits come straight back.
Studios
Same duo, six sets.
Every studio costs the same credits. One 15-second video at Standard 2K is 50 credits.
Orange Studio DuoThe classic orange seamless studio with one center mic.
Orange Street DuoNight street corner washed in orange light.
Orange Gala DuoOrange-lit ballroom with marble and a single mic.
Orange Retro Duo1970s television studio in warm orange.
Orange Pets DuoCozy orange living room built for two pets.
Orange Sunset Beach DuoGolden-hour beach set with one standing mic.Examples
Poster first, click to play.
Samples are rendered with synthetic faces, not real customers.
The classic orange seamless studio with one center mic.
Night street corner washed in orange light.
Orange-lit ballroom with marble and a single mic.
1970s television studio in warm orange.
Cozy orange living room built for two pets.
Golden-hour beach set with one standing mic.
AI Music Video Generator FAQ
Direct your own AI music video
Pick a set, upload two photos, and let LobbyDuo film the performance with the set’s own soundtrack. Preview free, then pay per video.