I notice we still have voicebanks that don’t have the Vocal Mode feature, and I remember they said they were going to add it to them eventually. Is that still happening? I would like to listen to Solaria with the belt append, or Eleanor and Anri.
For now, we received word that Koharu Rikka and Natsuki Karin will get them some time later.
SOLARIA was confirmed as well and is currently in progress.
Awesome. Thanks for the information.
More information about Rikka’s Vocal Mode update was mentioned in today’s TOKYO6 Livestream. xuu translated it on Twitter, so I’ll attach his links here.
Chifuyu was also mentioned, but perhaps it would be ready by the time she releases? It seems that Rikka just overall needs more data in order to be up to par and match the quality of Karin and Chifuyu, which is understandable since she was among the first AI vocals for Synth V. :o
Livestream source: 第6回TOKYO6公式生放送 - YouTube
New announcement from Eclipsed Sounds today with SOLARIA’s Vocal Modes! They revealed two variations: Soft and Solid. You can hear both of them in this mini clip on their YouTube account.
Source: https://twitter.com/eclipsedsounds/status/1529146152519553024
We might receive more for her, but we won’t know til they reveal them or if her update goes through and we find out as a surprise. .w.
Yep, just saw this. She sounds good so far.
Ooooh great! I can’t wait for this!!!
I just hope they implement a better way to blend the vocal modes. I want to be able to go from soft to belt, without having to use a separate track, and the transitions sounding unnatural.
honestly i think it depends on the voice providers choice, if they want to record different parameters for their synthv, the companys choice and funding. id love to see more with eleanor especially considering how lovely her AI sounds.
solaria actually is going to get voice parameters! but they need the funding first. so theres something :D!!
Are the vocal modes based on completely new recordings or is it just an AI analysis of the voice provider singing in a certain tone? Because if it’s the former it’s insane that Stardust has 8 modes
It seems that based on what’s happening to Rikka, it should be based on current recordings if there’s enough to create variations. Rikka’s AI voice is already a year old and she was only the second AI vocal to be released for Synth V (the only other one was Saki in December 2020, who is a first party vocal from Dreamtonics herself). Perhaps her existing recordings weren’t enough. TOKYO6 seems to want to use this opportunity to not only give her Vocal Mode with new added recordings, but to also improve her ranges and have her quality match Karin and Chifuyu.
Karin and Chifuyu don’t need additional recordings. The current ones seem to suffice to create Vocal Mode variations.
holy shit anri vocal modes will be real
Something about growling, vocal frying and other natural vocal effects?
I can’t wait to make Kevin and his friends sing with the voice of a rocker
KEVIN GROWL OGGHGHHHH YES PLEASE
It would be great if he had a yelling vocal mode, right now even with maxed tension, belt and solid he sounds a bit too weak for most western rock music.
i would have to disagree…! with solid+belt maxed out and on high octaves he sounds VERY powerful!
You’ll probably be able to change the vocal mode by setting a group to a specific vocal mode in the track, like languages.
Official announcement abour ANRI Vocal Modes
Why are the names for the vocal modes different for each voice?