#change cevio

[the-dragon-girl-27]

I feel like recently I've been doing lots of art i forget to post I should stop forgetting to post maybe ill spam old art i forgor to post at some point

I drew these back when that KAFU game was announced, It doesnt have costumes or modules like project diva from what they've shown i wish they did those here is my ideal world of where they did

[vocaloid-tunes]

Vulgar | Utsu-P feat. Ci flower

[late-night-vocaloid]

wait wait put your favorite vocal synth songs that you don't necessarily know if people would know in the tags (any level of popularity dw too much about it), the kind you can't stop replaying. what would you tell people to go listen to right now.

[cindersnowsstuff]

My 2024 bingo card sucked so I'm reusing it for 2025. Some of these are planned but they don't count until they release

[bmpmp3]

holy FUCK IA's voisona 2.0 is OUT

[nitw]

i think synthesizer v and just vocal synths in general are a perfect example of how ai technology isn't bad in its own right, but it all comes down to how it's produced and used and who it affects.

the voicebanks made for synthv, vocaloid, cevio, etc are all based on recordings from Willing Real Life People As A Job and the effort that goes into perfecting the technology so that anyone can make something that sounds great and unique as long as they know what they're doing IS SERIOUSLY IMPRESSIVE.

and while i think synthv is the only one that really relies on any kind of ai features, it's only for things like automatically tuning small changes in pitch, or the length of consonants and vibrato, to make the pronunciation sound more realistic in real time. it's a handcrafted system, the voice providers only do about half the work. and most importantly; everything still comes down to the user's own skills, creativity, and understanding of how the program works. there's no cheating around it if you wanna make something really good!!

[lesbian-forte]

Criticisms of Vocaloid and why I like SynthV

I'm not trying to change anyone's mind here, but I would like to say my piece after certain takes seem to miss the point entirely. This might be a bit of a rant.

Vocaloid has gone stagnant in recent years. Yamaha doesn't care. Yamaha doesn't need Vocaloid and is a large corporation that gets much more money off of their DAW software and actual instruments as opposed to something as niche as vocal synths that are both only big in Japan and also only if they're in the top ten or so.

Yamaha stopped putting effort into Vocaloid during the V4-V5 transition. There is a reason V4 has so many cancelled voicebanks. Several developers were working on V4 and Yamaha rendered their devkit suddenly worthless. Devs would have to purchase a V5 devkit and start work over, or quit Vocaloid. And as vocal synth companies are generally very small, few of them would want to continue or even be able to afford it.

So they moved. Miku splitting off for Piapro gave them an opening, and others started looking for alternatives. Then IA went to CeVIO. And more and more. And by the time V5's sun was setting, all the third parties that worked on that were gone too.

But for a while, you didn't hear much from most of them. If a company released a V4 at the tailend of its lifespan or a V5, they had to wait for exclusivity to expire. And Yamaha's exclusivity deals are harsh (ending distribution of existing song voicebanks in the case of utaus with the same VP) and long, borderline predatory. So voices that companies wanted to update couldn't receive them until those expired, or else refresh that deal and stay constrained by a company that didn't even want to bother with them.

So, come V6, Yamaha was desperate. Internet Co had made an ultimatum that if a Vocaloid 6 didn't come out soon, then they'd be going too. That was their last, and after Crypton packed their bags, most important third party. So they accelerated their plans and looked at what the new guys were doing to be so successful.

They took the wrong lesson.

AI is not inherently better. Sample-based voicebanks will always have their place. Traditional samples can allow an unnaturally large range and harsher voice acting than would be possible to maintain. AI is more accurate to the voice provider, and you have a greater degree of freedom with its tone, plus updates and additional features are so much easier- but Yamaha took 'AI' at face value and made a low-quality copy that sounds significantly worse than prior Vocaloid versions and pushed it with Gumi. They could have stuck to improving their concatenative synthesis render quality further- that's what SynthV started as, R1 was just a very well-rendered sample-based program that is probably just a fancy utau under the hood.

But Vocaloid jumped on the bandwagon by doing the absolute bare minimum and claiming the ear-grating engine noise that can cause actual nausea is remaining faithful to the 'Vocaloid sound' even though styrofoam on the mic and a sometimes pleasant metallic twang sound nothing alike. They didn't improve accessibility, V6 has the same stability issues as V5, and the shiny new feature Vocalochanger is just RVC but worse.

Then, less than a year after product launch, they start up VxB and don't do anything to improve the software they're actively selling. Internet Co themselves called this out in the form of a Gumi tweet. Then Internet Co got in talks with Tokyo6 and saw a possible out, so they gave it a go. They're still under contract by Yamaha so what they can do is limited, but we saw them stray as well. And the result is a much better quality version (though arguably still worse than her V4) despite being an exact port.

We're still getting a Gumi Solid V6 because V6 can't do emotions and they still have to be separate banks, and VxB still got a major update even though it's dying in April with radio silence for V6 development, while CeVIO/VoiSona is releasing 2.0s that get major acclaim like Ci Flower's reputation totally getting turned around, and SynthV is sitting pretty with several voicebanks announced and several coming out in December alone, and the most recent in-progress update including both voice-to-midi (which is what vocalochanger should've been) and Spanish.

I do not like V6, V5, or Yamaha. It could've been amazing for Gumi or Una to get updates so they'd have crosslang (or better crosslang) capabilities, as I work in English. But the result was extremely poorly implemented and Yamaha has made no effort to fix that.

I use SynthV all the time, I'd do the same for CeVIO if it offered crosslang as well rather than just dictionaries and a couple English banks. I'm not against trying new things. But I either want the other programs to have the things to suit my needs in a quality manner that's intuitive to use or for the voicebanks I love to get versions on programs that already do. It's not that complicated.

The jokes and the yammering from rabid SynthV fans dissing Vocaloid can get to be too much sometimes. But you have to consider where that actually comes from. It's in response to suddenly being spoiled with a cheap, accessible, high-quality program when the expensive, poorly constructed, difficult one has been dominating the market with anti-consumer, anti-third party practices for years.

P.S.: Also you can do robotic tuning and mixing on realistic vocal synths, it's called doing the same thing as before and then adding it in post. You think utaites swallow vocoders or something? No, they just use different tools to get the same result as engine noise. Not fighting the voice when you're trying to go for realistic vs manual tuning and adding some very easy effects on when doing it the other way around is better, actually.

[deadly-espresso]

So uhhh development on my next song might be delayed

So umm I have been working on a new English song over the next couple of weeks, but recently, I've hit a bit of a roadblock. Weirdly enough it's not about the song itself... it's about the vocals.

So basically I had started by composing the vocals in SynthV, and what I had intended to do was run the vocals through a KITS AI model to make the voice sound different (I had previously done that with my MIRA remix). I intended to use the KITS AI model for TessTess (whom you may recognize as an UTAU voicebank) for my song because I thought it would fit the tone of my song very well (it was a youthful-sounding male vocal, it sounded a bit similar to the VOCALOID/CEVIO voicebank Flower in terms of quality). However, it recently turned out that due to changes to KITS, most if not ALL voicebanks made for the program had been made private without the input of their creators, and there is a possibility that TessTess' voicebank may have been deleted.

I did reach out to the creator of RiKU (RiKU and TessTess's creators used to be affiliated for some time) for help regarding the matter. I was able to regain access to RiKU's KITS AI model, but unfortunately I couldn't regain access to TessTess' KITS AI model because according to RiKU's creator the TessTess model had been deleted and sadly couldn't be recreated because they didn't have room for more models (Even then, they likely couldn't recreate the model without authorization from TessTess' creator)

So, yeah, I don't know what to do now. The only english AI models I still have access to are the SynthV lite models for Tsurumaki Maki, ANRI, Eleanor Forte, and Solaria. If you can provide any assistance regarding this matter, that would be highly appreciated.

[glaceplatz]

I drew Flower's CeVIO design a few days ago and changed it a little bit, the only thing that bothers me about this design is the orange in her shorts and in her boots.

[tomedonaki-hakujou]

thoughts on synthesizer v kafu. copypasted from twitter but also elaborated on a bit more

things are a bit different between the "initial production of cevio kafu" and "current success of cevio kafu"

kaf is older now, and kafu proved to be a popular success with her own voice who can reach further beyond kaf

at the time, a few years ago, wouldn't have been the right timing for a "kaf 1:1 voicebank" i think, especially with kaf being as young as she was.

but kaf, she's older now, her growth partially attributed to kafu's hit popularity and her other works as well

we know kafu can stand on her own as "kafu" and not just relying on "kaf"

and with kaf's new step into adulthood, so the timing is right for a new kind of "kafu"

even in the 4komas, kafu learns who kaf is, wants to sing better, trains harder for her SV

pied has said that, the beauty of the musical isotopes is the preservation of one's voice at a specific moment in time.

kafu cevio captures kaf's teenhood, kafu SV captures kaf's young adulthood

and that sort of fits thematically into kaf's music as well 🤔

kafu SV is absolutely an older kafu. her proportions are taller, "phony" lyrics use "watashi" instead of "atashi"

the fact kafu SV exists at all is proof of growth as in, one could change their mind, one could be open to new "possibility" after she proved herself

after all, kafu's name represents "possibility + mystery." why wouldn't she be full of possibility? kafu SV continues to embody that sentiment, and even further it by being available to new kinds of people. it's not about how she sounds, it's about the mission of the isotopes

kaf/VWP are undeniably intertwined with vocaloid culture and have their roots in it, and work closely with vocaloPs as well. kafu in the first place was always meant to sing with unrestrained possibilities with all her varying demo songs, showing the spirit of vocaloPs

those possibilities are only furthered now with kafu SV, now that kafu cevio has achieved her mission and succeeded in her own right as a unique vocalist, and continues to thrive

for mac/linux users, english/chinese users... and more. unbound expression. singing anything...

one thing kamitsubaki does on quite a wide scale is engage with the vocaloP community heavily, and encourage small creators and even highlight their works with the isotopes. for me, to be able to be a part of that finally with SV is exciting. i've always loved the isotope community

especially because my music influences are more closely aligned to japanese vocaloP, and musical isotope being the current active Big Thing, being able to engage in that community is something special to me and i trust in the new direction that SV kafu implicates by her existence

another thing, is that kaf's vocal ability has improved considerably in the past few years. a cutesy, uniform, artificial AI is suited to the younger kaf. a realistic, expressive AI is suited to the older kaf who has more singing experience, more power, expression, etc

overall i think there's a lot of meaning behind kafu synthV (and by extension (heh) the voicepeak extensions) on what the isotopes are meant to represent and how they're meant to be used. they've always represented unrestrained creativity and a homage/love letter to vocaloid culture as a whole. synthV and voicepeak only furthers those expressions -- talkloid is pretty big in japan too, so voicepeak lets musical isotope expand into that community, while synthV allows musical isotope to sing in new ways and reaching new people

[the-dragon-girl-27]

Vocaloid Collection doodles

Yellow by Shu and Self Proclaimed Angel by Katachi P

[kafus]

it's entirely possible that kaf has changed her feelings about kafu over the past few years, she's a bit older and the concept has had time to settle, but this stuff with synthv is really startling to me because like. back when kafu was in development for cevio, they ran a poll asking which voice people liked better, there were options A and B - A sounded wayy closer to kaf, like kaf in a box, and obviously pre-existing kaf fans voted for option A. it was a huge thing because kaf put out a statement saying like, i want kafu to be her own thing, and so we've decided we're not going with option A. this was a multi paragraph statement with a decent amount of emotion in it - kaf grew up on vocaloid, she started singing because she was interested in utaite, she has genuine interest in the culture...

so them turning their back on this creative decision a few years later just feels... odd?? piedpiper just put out a longer tweet on twitter about kafu's synthv but i'm not going to comment on it since i feel like machine translation is losing some nuance and i'm waiting on a friend to help me out with better translation, but kaf's tweet about the phony demo is really short and has pretty much zero emotion, it's like just a PR tweet. this isn't super unusual, kaf doesn't talk about a ton of stuff very publicly, but it still feels odd, like she's fangirled on twitter before about honeyworks using kafu, she's not incapable of being excited on main...

a lot of kaf fans that i follow are excited about this because they want kaf in a box and i'm not following enough vocaloid people to see the opinions on the other side of things, but i made some disappointed tweets and my jp mutuals liked them and. even from people who are tentatively interested or excited in her synthv, i'm seeing visible confusion about why they didn't go with "version A" from that poll years ago if they were just gonna do this years later, so at least i'm not crazy and even for people who want kaf in a box, this is whiplash lol

idk i just really wish i knew the behind the scenes of how this happened. i was relatively confident this wouldn't happen because of how passionate they've been in the past about differentiating kafu, including kaf herself, and this is just such major tonal whiplash. kaf is usually treated well by kamitsubaki as far as i know so i'd like to believe this was a mutual decision even if i don't agree with it and not like, her being pressured in some way or another

[iconsynth]

Anonymous asked: "hii! can i have light pink sekai (cevio) pfps? :3 to follow up the sekai ask, can i have some headers too if thats ok?"

Light pink Sekai icons/headers for anon! LMK if you'd like any changes!

Free to use; reblogs appreciated!

[daily-ghostly-goobs]

I don't know shit about CeVio to dump admittedly so we're skipping it, so UTAU is a free engine with user made voices. It's also abandonware since 2012 and is the sort of program where you need a lot of QoL plugins unless you want to have a miserable time with it. And while I could get into it far more than the following will it would sound unnecessarily mean and to anyone who works with it I love you, but yes it's that bad. If the programs old enough you have to change your computer local just for it to run properly on an english computer and you can't have more than one track at a time, it's that bad.

(There is a program called OpenUTAU that aims to be able to use a lot of the stylistic legacy plugins of UTAU while having a lot of QoL stuff be default but I've heard a variety of complaints some I don't understand and some I do. I respect the issues with messing with old plugins to get them to work, but I've also heard about how the envelopes of the tracks save being awful is one of the big complaints? Straight up not I'm techy enough to know what that means or why its bad)

Kasane Teto is the flagship, but she actually got an official high quality bank with SynthV. Apart from her it's probably Defoko or Utane Uta- but there's literally hundred of banks made by people out there.

Though speaking of synthV lot of things have partnered with synthV actually :)

Like, you'd be impressed! GUMI also has a synthV, she isn't exclusive to vocaloid! Stardust used to be but isn't now, and is also a synthV! Rosa was a Cevio only I think, and now isn't. Kafu is suspended indefinitely for synthV bank but they were *gonna*, Moca's come over just last week from VOICEPEAK, and in future Miki and Hiyama Kiyoteru are coming over from vocaloid :)

(it's not even unique for utau, Yamine Renri is also a synthv and has been for quite some time)

This turned out to be about synthV again. It wasn't supposed to be. here is a UTAU bank song with Kasane Teto https://www.youtube.com/watch?v=4llHpe3WlFw and SynthV Teto https://www.youtube.com/watch?v=oGS6_rFsAe4

Neither of them are really "popular" songs but this is my rant and I can link what I want to. This also concludes this ask chain, because from here everything gets significantly more obscure and tbh if you wanna know you'll fine 'em eventually.

DAY 253 - ‘GOLDENGATE’/‘BURN IT DOWN’ (Click for better quality)

Well, this chain of explanations definitely was informative! It’s really clear that you are quite knowledgeable on this type of stuff, it was fun reading through these asks. :p

[bmpmp3]

even though i enjoy plenty of vocals like this, im not a huge fan of like the trend of when a vtuber/utaite/etc voices a vocal synth and then they just have the design look like their persona but like with white hair or smth. like its fine its not that deep but i wish they made more independent characters, i think its more fun that way

[vocalsynthbdays]

heelo !! im really sorry ive been gone for so long. smthing happened, then another, then another, and it just made it really hard for me to come back

i meant to return sooner, so im again really really sorry for being away so long, and especially that i left so suddenly and without explanation

im still really busy and unfortunately cannot go back to posting right now, but i wanted to come on and just explain i havent like, abandoned this acc.

i really want to post for the next full year, but atm im not sure if ill be able to

again i am just so so sorry about this, i absolutely love posting on here but i just couldnt for a while

here are the birthdays i missed as well as just the rest of the year in case i dont get back

some of these might be wrong or inaccurate as i check on the day i post, and so i havent gotten to check these. also my reasons for choosing the date i did for each birthday might be unclear, as its unfortunately not as simple as it sounds in some cases ashidhajkska same with which engine i put down

kanade kanon- vocaloid beta- nov 11 yurika sayu- utau- nov 11 alyx- utau- nov 12 ka-chanloid- utau- nov 13 koeno tsubasa- voidol- nov 13 ci-chan- vocaloid beta- nov 13 kasukabe tsumugi- voicevox- nov 14 kagami kawaiine- fanloid- nov 15 yan xi- muta- nov 15 yokune ruko- utau- nov 17 rook- utau- nov 17 zing- vocaloid 4- nov 18 shion magi- utau overseas- nov 19 tanaka san- voisona- nov 19 dex- vocaloid 4- nov 20 daina- vocaloid 4- nov 20 taya soune- utau- nov 20 yowane haku- fanloid- nov 21 akita nero- fanloid- nov 21 momone momotaro- utau- nov 22 darling- utau- nov 22 nonoshi- utau overseas- nov 23 setty- deepvocal- nov 23 saros- synthv studio- nov 24 chiyu- synthv- nov 26 MeAw- vocaloid 2(?)- nov 26 denatsu sora- utau- nov 27 kikiyo sai- fanloid- nov 28 amane kana- voiceroid- nov 30 qing su- synthv studio- dec 1 marie ork- alter ego- dec 1 mintau mintira- utau- dec 1 asterian- synthv studio- dec 2 whisper笘・ngel sasayaki- macne series- dec 2 nurse robot_type t- utau- dec 3 kiyoteru hiyama- vocaloid 2- dec 4 kaai yuki- vocaloid 2- dec 4 miki sf-a2- vocaloid 2- dec 4 tsukuyomi ai- voiceroid- dec 4 tsukuyomi shouta- voiceroid- dec 4 makune hachi- utau- dec 4 zundamon- utau- dec 5 kiana- sharpkey- dec 7 jin- synthv studio- dec 7 ayama- synthv studio- dec 7 utatane piko- vocaloid 2- dec 8 zhiyu moke- vocaloid 4- dec 10 hide- vocaloid 3- dec 10 audine- maghni ai- dec 10 xuan yu- synthv studio- dec 12 cong zheng- synthv studio- dec 12 mizuo- utau- dec 12 ring suzune- vocaloid 3- dec 12 tomero chii- utau- dec 12 tone rion- vocaloid 3- dec 16 meito- fanloid- dec 16 hanazono kotone- voidol- dec 16 rosa- cevio ai- dec 17 rin no youchuu- fanloid- dec 17 maita- utau- dec 17 (repeate) daichi- utau- dec 17 maika- vocaloid 3- dec 18 ona- vocaloid 3- dec 18 kirune- voisona- dec 19 aisuu- voisona- dec 19 oliver- vocaloid 3- dec 21 popy- cevio ai- dec 21 rose- cevio ai- dec 21 kumo noizu- utau- dec 21 big al- vocaloid 2- dec 22 avanna- vocaloid 3- dec 22 cul- vocaloid 3- dec 22 yuzuki yukari- vocaloid 3/ voiceroid- dec 22 kizuna akari- voiceroid 2- dec 22 nene nene- utau- dec 22 clara- vocaloid 3- dec 23 bruno- vocaloid 3- dec 23 meril- vocaloid 3- dec 24 genbu- synthv- dec 24 merrow- neutrino- dec 24 yamine aku- fanloid- dec 24 miko ooka- utau- dec 24 salvador- utau- dec 24 iro nanine- utau- dec 24 mitarashi mary- voiceroid- dec 25 oniko hinomoto- utau- dec 25 len kagamine- vocaloid 2- dec 27 rin kagamine- vocaloid 2- dec 27 dong fang zhi zi- utau- dec 27 iku acme- utau- dec 27 magene shito- utau- dec 30 saki- web synthv- dec 31

again i am so so sorry for being gone

if any more changes arrise, like me not being able to post next year, ill try to post about more explanation, and not just disappear

im thinking of making a neocities or other website and kind of reposting all the stuff from my social media posts on there, so that theres kind of like a permanent place for it all ? idk, i just like the idea of being able to post about vocal synths like this without the pressure of a daily deadline ahsdjakka