Verses, Inc., led by CEO Sean Lee, has unveiled a landmark partnership with SM Entertainment to launch a bold new music-tech initiative. Central to the collaboration is “Rappie,” the world’s first multimodal AI Rapmaker, introduced in beta by Verses this June. Designed to democratize music creation, Rappie combines text input, rap composition, and video generation into a seamless experience—enabling users to produce polished rap performances instantly, regardless of musical background. This breakthrough marks a significant step forward in user-driven, AI-powered music innovation.

As part of a new artist project from SM, the collaboration plans to feature official tracks produced with renowned composers and culminate in an immersive XR (Extended Reality) concert. Verses' 'Rappie' technology will provide a unique experience for fans, allowing them to connect with artists in a new way by not just listening to, but actively co-creating and interacting with their music.

From Keyword to Rap—Complete Content Generation in Seconds

Rappie empowers anyone to create rap content with no musical expertise required. The AI interprets input text to generate lyrics, rhythms, and voice performances that match the intended theme and emotion. Avatars then deliver expressive performances, syncing facial expressions and body movements to produce a polished, high-quality stage.

The beta version of Rappie introduces a wide range of innovative features that redefine how music is created and experienced. Users can generate rap lyrics and vocals entirely through AI, without any prior musical background. They can choose from a diverse library of themed virtual stages to match the mood and message of their content. Avatars—either personalized or styled after celebrities—serve as performers, delivering expressive, synchronized shows. The platform also enables users to create short-form music videos with dynamic, cinematic camera movements, giving each performance a polished, professional feel. Additionally, real-time interactivity allows users to touch elements within the virtual stage—such as the avatar or background objects—to remix the audio and visual components on the fly, offering a highly engaging and customizable creative experience.