Hear me out if Macne Nana synth v does happen and she doesn’t bring French support we ride at dawn
This is all theoretical
This is all theoretical
New profile posts
Why do people expect Vocaloid\UTAU voice to sound the same once it's been remade into AI?
It's already been made clear that the voice providers sound different than the old synthesizers.
Why put in such an expectation? Vflower's voice is clearly machine-sounding and all of it's traits are due to the compressed nature of the samples + the Vocaloid3/4 engine warping them.
Of course the VP can't sound the same. I see people make remarks about UTAU Ritsu sounding better than the AI Ritsus when it's clear that the UTAU VB samples were cherrypicked to sound consistently shout-y to a non-human level. Nobody sings like that. Canon doesn't scream when she sings, it'd strain the voice too much. Of course the UTAU is going to always sound powerful when the samples were made and picked to sound that way.
I think it's unreasonable that people think the AI is simply going to be "automatic tuning generator" when the AI is actually a recreation of the voice provider's singing.
Training an AI voice directly on top of the UTAU rendered voice is going to make it sound low-quality due to the double synthesizing.
I get that we all have nostalgia for the old chunky sound of a previous generation synth, but AI is more welcoming to producers who don't want to deal with all the manual tuning. It's simply easier to use and sounds better by default.
And we can still keep our copies of the old previous gen synth.
It's already been made clear that the voice providers sound different than the old synthesizers.
Why put in such an expectation? Vflower's voice is clearly machine-sounding and all of it's traits are due to the compressed nature of the samples + the Vocaloid3/4 engine warping them.
Of course the VP can't sound the same. I see people make remarks about UTAU Ritsu sounding better than the AI Ritsus when it's clear that the UTAU VB samples were cherrypicked to sound consistently shout-y to a non-human level. Nobody sings like that. Canon doesn't scream when she sings, it'd strain the voice too much. Of course the UTAU is going to always sound powerful when the samples were made and picked to sound that way.
I think it's unreasonable that people think the AI is simply going to be "automatic tuning generator" when the AI is actually a recreation of the voice provider's singing.
Training an AI voice directly on top of the UTAU rendered voice is going to make it sound low-quality due to the double synthesizing.
I get that we all have nostalgia for the old chunky sound of a previous generation synth, but AI is more welcoming to producers who don't want to deal with all the manual tuning. It's simply easier to use and sounds better by default.
And we can still keep our copies of the old previous gen synth.
pros of synthv being so good: it being so good
cons of synthv being so good: when i use any other synth, i keep thinking how easy working in synthv is and getting lazy 🦥
cons of synthv being so good: when i use any other synth, i keep thinking how easy working in synthv is and getting lazy 🦥
Mai latest wip because mixing the medley is hell on earth lol so Im taking a long break... first time using Mai and I'm not that big a fan? shes good but lots of loud recordings that you have to fix and she handles pitch way differently than Feng Yi but the price can't be beat! Shes a place holder until Miki is released :) I tried to base the tuning on Shizuku (feng Yi... which is what I try to tune Feng yi like anyway sooooo) and Airi (Mai) from project sekai for this song ;-;
Just heard about someone delayed due to mechanical issues on multiple airlines during the same trip. (Plane wasn't broken the second time, though.)
I have a new business idea.
There's also a supersonic model.
'Cause we need good, clean, reliable, well-maintained, non-outrageously-expensive transportation.
I have a new business idea.
There's also a supersonic model.
'Cause we need good, clean, reliable, well-maintained, non-outrageously-expensive transportation.
The vocal synth collectors thread has taken quite a shape! Several synths got completed 100%, several above 60%, missing Cantor and much of V2, V3 and Voisona.
vocaverse.network
Resource - Vocal Synth & Voice Bank Physical CD Collectors Thread
Do you prefer having a vocal synthesizer, or voice banks thereof, sitting on your shelf, rather than digital downloads? Perhaps, you barely even compose music at all, but you still enjoy collecting your favorite singing robots, just like others collect their favorite video games! One day, your...
vocaverse.network
Okay...I think I'm going to finally set on getting a HDD for my laptop. For my Music/Videos/and spare copies of my vocaloids and editors with a doc of all their codes. Than maybe I'll just get a yearly Onedrive of 100 GB for just my Word docs of my fanfics and original stories attempts (only like 1 complete novel...lol, and a halfway done one from long time ago)
There is a Toshiba Canvio Basic of 2TB I'm thinking of getting, but it's in Amazon. Or a 2TB Western Digital from bestbuy....I just need to remember my password...
There is a Toshiba Canvio Basic of 2TB I'm thinking of getting, but it's in Amazon. Or a 2TB Western Digital from bestbuy....I just need to remember my password...
Happy anniversary to 
!
!
man im annoyed i worked so hard on that avril lavigne cover with yi xi only to not be able to post it anywhere bc of copyright claims lol. i wanna post a cover with yi xi but idk what i want to make now...
I really love Kurita Maron and Goki in Voicevox singing
someone save the cryptonloids from piapro nt, i just listened to cute na kanojo from proseka WTAF did they do to Luka 
Happy anniversary to 
!
!
I think judging voicebanks from demo is like judging book from cover. Why don't people just try it themselves before give an opinion. Bashing vbs without even try is not cool.
Starting to refine my Vocaloids' personalities:
-Miku is outgoing, kind, intelligent and altruistic.
-Gumi is laid-back, easy-going and cheerful, an optimist who goes with the flow.
-Avanna is gentle, reserved and polite, with a heart of gold.
-Not a Vocaloid, but Teto is cheerful, eager, and determined, with a mischievous streak and a desire to prove herself. (also she's really fun to draw)
-Miku is outgoing, kind, intelligent and altruistic.
-Gumi is laid-back, easy-going and cheerful, an optimist who goes with the flow.
-Avanna is gentle, reserved and polite, with a heart of gold.
-Not a Vocaloid, but Teto is cheerful, eager, and determined, with a mischievous streak and a desire to prove herself. (also she's really fun to draw)
I'm already seeing more hype around to xi because of butcher vanity another w for SynthV
I finally got Word again after so many years without it, like a week ago...but the day after Onedrive is expired and I have like a month or 2 left before I lose so many important stuff (like V4 to V6... and FL Studio) just my luck!! 
I still need to get a better SSD for my laptop. But I think I need to get something else that will save all my files to transfer to the new ssd? *sigh* unless i bite the bullet and just buy a yearly onedrive.
I still need to get a better SSD for my laptop. But I think I need to get something else that will save all my files to transfer to the new ssd? *sigh* unless i bite the bullet and just buy a yearly onedrive.
Why does the best voices in Vocaloid and Synth V have the ugliest designs?
Everyday I log on in hopes of Miki synth V news and every day I leave sad :<
How a melodyne can cost this much, especially the full version, is like 699-899usd. . .
Hands down, favorite Gumi design ever.