Verses is pioneering interactive music, where music, storytelling, and visuals evolve and transform based on user interaction rather than being a passive listening experience. Interactive music takes various forms, and one of its most notable examples is aespa world, an interactive music world that merges music with the metaverse.
Developed in collaboration with SM Entertainment and built on Naver Z’s metaverse platform, ZEPETO, aespa world is a space where K-pop meets generative AI-powered interactive technology. Its technological excellence was recognized when it won the CES 2025 Innovation Award.
aespa world is not just a virtual space; it is a new concept of an interactive music world where users can experience aespa’s universe, create music, and engage in immersive interactions. The world’s design plays a crucial role in bringing aespa’s lore to life within the metaverse. This intricate design process involves encouraging user interaction and visually embodying aespa’s themes and universe.
In this interview, we dive into the behind-the-scenes stories of aespa world’s design, as told by the talented planners and designers Kang Jung-woo, Jang Su-ji, and Lee Ju-yeon, who crafted this remarkable experience.
<aside> 💡
Eun-Gyeong Kim : Moderator
Jung-Woo Kang : Planner, Designer
Joo-Yeon Lee : Planner, Designer
Su-Ji Jang : Planner, Designer
</aside>
Jung-Woo Kang.
Joo-Yeon Lee.
Su-Ji Jang.
Eun-Gyeong Kim: aespa world began as a completely new concept—an interactive music world. What were some of the challenges you faced in the initial design phase?
Verses’ Beat-based AI Music Video Generator.
Jung-Woo Kang: This project originally stemmed from the "Beat-based AI Music Video Generator" technology, which won an Innovation Award at CES 2024. The core idea was to allow users to edit characters in real time in sync with music. However, when we tried to implement this within the ZEPETO platform, we encountered unexpected technical limitations. One major challenge was that ZEPETO’s development environment differs significantly from Unity, which led to a lot of trial and error.
(Laughs) Oh, and at first, we were super excited, thinking, "Wow, this is going to be something amazing!" But when we actually started working with ZEPETO, we found ourselves asking, "Wait… can we even make this work?" (Laughs)
Joo-Yeon Lee: ZEPETO is fundamentally a 3D-based virtual space, but it is optimized for mobile experiences. Because of this, some of our initial technical ideas had to be scaled down. However, rather than seeing this as a limitation, we adapted to the platform’s environment and ended up designing a more intuitive and playable experience for users.
Naver Z’s metaverse platform, ZEPETO.
Jung-Woo Kang: Initially, we tried to apply the Beat-based AI Music Video Generator technology directly into ZEPETO. However, after considering ZEPETO’s user culture and technical limitations, we realized we needed to adjust our approach. That’s how My Stage was born—a feature that transformed the concept from users freely manipulating music and characters into a more intuitive interactive experience.