South Korea-headquartered entertainment giant HYBE is leaning more and more into artificial intelligence in music.
The company has just unveiled a virtual pop group called SYNDI8, whose voices were developed using AI technology.
The technology used for the group’s voices was developed by AI audio company Supertone, which is majority-owned by HYBE, after it struck a $32 million deal for the tech in 2023.
Founded in Seoul in 2020, Supertone claims that its software can create “hyper-realistic and expressive voices that [are not] distinguishable from real humans.”
This technology aligns with comments made by HYBE Chairman Bang Si-Hyuk in a 2023 interview with Billboard, in which he said: “I have long doubted that the entities that create and produce music will remain human.
“I don’t know how long human artists can be the only ones to satisfy human needs and human tastes. And that’s becoming a key factor for my operation and a strategy for HYBE.”
The new virtual pop group, SYNDI8, pronounced “Syndi-eight,” is a four-member girl group, comprising virtual members Canary, Nest, Goyo, and Raven.
HYBE’s Supertone says they exist within the virtual world of ‘Nansy Land’.
NANSY is also the name of Supertone’s foundation model – which stands for Neural Analysis & Synthesis.
Supertone is led by AI expert Kyogu Lee (Supertone President). In an exclusive interview with MBW last month, Lee explained that the company’s NANSY model “serves as the backbone of Supertone’s speech synthesis technologies”.
“NANSY has the special ability to divide and re-assemble voice components – timbre, linguistics, pitch, and loudness – individually and independently, generating natural-sounding voices with unparalleled realism,” Lee said.
You can read the research paper for NANSY, here.
In its announcement about SYNDI8, Supertone said it aims to “explore the applications of [its] technology in the music content business and to cultivate [its] own voice intellectual property (IP) to demonstrate the capabilities of [its] creations”.
HYBE previously showcased the possibilities of what it can do with Supertone’s technology in May last year when it released a single called Masquerade from an artist called MIDNATT – described as HYBE’s first AI-powered artist.
MIDNATT, the virtual alter-ego of HYBE-signed artist Lee Hyun, used a prototype version of Supertone’s real-time voice-changing tool Supertone Shift to “seamlessly” transition between his own vocals and the vocals of a female singer on the track Masquerade.
That same track was touted by HYBE as the “first-ever multilingual track produced in Korean, English, Japanese, Chinese, Spanish and Vietnamese”.
Most recently, HYBE’s new virtual group has released a three-track album called MVP, which features lead single ATOTA (short for Any To One To Any), My Fantasy, and True Color, with the latter track adopting a modern R&B style.
You can hear the lead single, ATOTA, below:
“SYNDI8 is a virtual artist group born from Supertone’s voice synthesis technologies, inspired by the company’s growth story. Embodying the fantasy universe, the group plans to engage with fans across various platforms.”
Deja and Han, SYNDI8
An animated story titled Magic Voice Prism: The Journey Begins was also released alongside the album.
“SYNDI8 is a virtual artist group born from Supertone’s voice synthesis technologies, inspired by the company’s growth story. Embodying the fantasy universe, the group plans to engage with fans across various platforms,” said SYNDI8 co-producers Deja and Han.
HYBE also demonstrated the capabilities of its proprietary AI on its Q1 investor call, when HYBE’s CEO Jiwon Park consented to having his own voice cloned using Supertone’s ‘voice synthesis technology’.
Last month, MBW asked Supertone President Kyogu Lee if the company’s tech will be used to recreate the voices of superstars like BTS.
He told us: “While Supertone is theoretically capable of creating an infinite number of new and original voices, as well as recreating existing voices, we are devoted to prioritizing the rights of all artists and creators, including those under HYBE.”
Supertone’s work has also been featured in Disney+ and Netflix series.
The company says it is expanding its reach to support creators with tools like its AI noise reduction plug-in Supertone Clear and voice changer Supertone Shift, which launched in April.
SYNDI8’s debut arrives amid the ongoing debate about the use of AI to create and recreate voices in the music industry.
Music Business Worldwide