SuperTone, a South Korean company recently acquired by Hybe, has debuted a realtime voice changer powered by artificial intelligence called Shift. It’s now in pubic beta until June.
There are so many far reaching implications from this technology that it’s staggering to compute. At first glance, this could be a fun way for a single performer to alter their voice to perform each part of a male/female duet. Think Barbra Streisand & Neil Diamond’s “You Don’t Bring Me Flowers,” or Diana Ross & Lionel Richie’s ‘Endless Love” sung by one person. Or a singer/songwriter being able to create a complete song with male and female backing vocals…the possibilities are endless. But also, there’s a darker side with disingenuous, or worse, individuals impersonating the opposite sex. In an ever-changing world where one is having a harder and harder time determining what is actually real and what isn’t, reality is becoming blurred beyond comprehension.
SuperTone Shift
The easiest way for electronic musicians to get their music onto Spotify, Apple Music, iTunes, Amazon Music, Tidal, Instagram, Facebook, TikTok, Pandora, Twitch & much more! Click the banner above or the Go Button to save 7% off of your signup! GO!
SuperTone is now offering Shift as an open beta for Mac and PC. The app showcases the technology in a very compelling manner and you can try it out yourself. SuperTone even states that they can create a custom voice for you. Now, we’ll get more into the features of Shift, but here’s where it gets even more interesting. Hybe, the publicly-traded music company behind K-Pop superstars BTS, has purchased SuperTone for 45 billion South Korea Won (US $31.75 million). Why would a boy-band music company purchase an AI voice-changing concern?
Hybe claims that it is in “diversification mode” after the expansion of its games division, as well as the $1 billion acquisition of Scooter Braun’s Ithaca Holdings. But could a new portfolio of AI generated Avatar artists be the next push, even if they have announced NewJeans and Japanese boy band &TEAM?
Shift is suited for YouTubers, content creators and gamers, as well as anyone who wishes to accurately express their chosen persona’s voice.
About a year ago, Hybe released a new single called “Masquerade” from an artist called MIDNATT, which showcased the possibilities of what it can do with SuperTone’s artificial intelligence technology. MIDNATT, the alter-ego of Hybe artist Lee Hyun, used SuperTone Shift to transition between his own vocals and the vocals of a female singer on the track “Masquerade.” Hybe boasted that is was “first-ever multilingual track produced in Korean, English, Japanese, Chinese, Spanish and Vietnamese.”
Lee Hyun reportedly sang the track in the six languages, and using SuperTone, “the pronunciation data of native speakers was applied to the track to further refine the artist’s pronunciation and intonation.” With the latest version of SuperTone Shift, users can “immediately switch to their desired voice” from a library of ten predefined voices in real-time, with their voice analyzed for conversion “within 10 seconds.”
MIDI Designer Is Now Free!
MIDI Designer Pro X is now free to download! MIDI Designer Pro X is a professional-grade MIDI controller platform for iPhone, iPad and Mac. User-contributed layouts let you control everything from Ableton to Yamaha out of the box. Go beyond hardware and express your musical vision. Check out out now!
SuperTone Shift Features:
- SuperTone’s Shift offers real-time voice changing technology. It lets users immediately switch to any selected voice. Just pick a voice and begin speaking.
- The Voice library currently has 10 high-quality voices curated by Supertone. New voices will be added regularl.
- Voice blending: Choose a voice and adjust your blend ratio between the AI and you.
- Customize your voice by adjusting parameters such as pitch, pitch dynamic and reverb.
- Easily integrate with your favorite apps like Discord, VRChat, and Twitch for seamless connectivity.
- Supertone Shift has best-in-class latency (down to 47ms), as close as possible to real-time.
- Experience high-quality voice conversion on any device, no GPU needed.
