#cevio ai talk

[voca-song-a-day]

Today's featured song is: "Shadowman Show" by NashimotoP feat. Koharu Rikka!

[takoyakidonuts]

Voicepeak HARU Officially Releases! + CeVIO AI Talk UNI-Chan Release Date and Pre-orders Revealed!

After plenty of waiting, HARU’s Voicepeak bank is now released and available for purchase! Voicepeak HARU Official Demo Video As previously reported, HARU’s expressions include “enthusiasm”, “happiness”, “anger”, and “sadness”. With this release, now many people are curious if KAFU will receive a Voicepeak bank as well or if they’re now fully focused on KAFU’s SynthesizerV bank which was…

[bmpmp3]

give him to me NOW!!!!!!!!!!! or i'll settle for a release date pwetty pwease

[novaspurgatory]

Glow down era booo tomato tomato

First one was like 4+ years ago second one I made today in like a few minutes

Blehhh :p

[synthvnews]

COKO has been announced for VOICEPEAK, talk engine by SynthV developers! 🎉

Prepare for her release in January 2024 - preorders start this November.

[fzkr-sndr049]

HARU canonically a massive otaku fr

[vocaloid-song-of-the-day]

Gnossiennes by Otonashi AF feat. Hatsune Miku and #kzn

[vocalsynthbdays]

happy birthday Suzuki Tsudumi(cevio cs) and Mimi Yorune(utau) !!!!! [feb 23]

(tsudumi)

(mimi)

Suzuki Tsudumi is a japanese synth developed by the CeVIO Project, and originally released on 26 sep 2013. she is voiced by Inami Anju and illustrated by Saito Masatsugu. tsudumis character birthday is feb 23. she also released for cevio ai on 9 sep 2022, voisona talk on 1 sep 2023, and voisona (singing version) on 26 sep 2023.

Mimi Yorune is a japanese synth created (voiced and managed) by moonst4r, and initially released on 4 apr 2011. mimi is illustrated by a few different people, but the art im showing is by subaloid. mimi has banks available in english also. her character birthday is feb 23, and she is a witch. shes a part of the utau group NOCTE, consisting of her and Souta Kumori

[innocuous-gnome]

at any given moment i am vibrating with the need to infodump about vocaloid

[autisticlio]

The Steam label for generative AI was primarily made as a warning that a game has stolen assets for a commercial product. But here, the assets aren't being stolen and were used with consent. So it results in people thinking SynthV and Cevio as the same thing as Chat GPT or dall-e.

Bandai Namco really said "I'm gonna unintentionally cause the biggest drama for people who use Cevio and SynthV by marking the game we released as using generative AI despite both basically just being fancy autopitch."

[tentakilly]

Alright gang. We’re gonna talk about the project of mine that’s least likely to come to fruition because of how complicated it would be to make it. And that my friends is ‘(V)Flower the Punk Magical girl’.

First comes the Licensing. First I have to have permission from Crypton, Yamaha, twindrill, the guys who made CeVIO, the guys who made Synthesizer V, and various Utau creators. It’s not the actual getting permission part I’m worried about it’s the way I believe some characters I’m afraid could strait up not be used in the way I need them to be used. Example: Hatsune Miku. I don’t think Crypton would let me depict her as a villain if I’m going to use her. Even though she would be a miss guided character.

Second issue: music. Very simple. Some artists are less likely to work on a project like this than others and won’t be likely to let me use their music.

Third issue: language and making the characters talk. Most of the characters I plan on using for this project don’t have talk voicebanks(Oliver, Yohio, The Kagamines, Solaria, Kevin, Sweet Ann, Kasane Teto, Gumi, Utane Uta(Defoko), Momone Momo, Etc). Not only that I have to either make this in Japanese or English and because a lot of the voicebanks don’t normally have the capacity to do both languages in an understandable way it would be incredibly expensive and time consuming to do the tuning and actually talking.

Forth issue: Animation. It would be animated with 2D for the characters and 3D for the Setting. I hope why everyone knows why that’s really hard right.

Fifth: The audience. Out of all the vocaloid characters to get a potential movie VFlower is among the least likely because she’s not Miku. Anything but The Crypton Loids and Otomachi Una. It’s simply wouldn’t sell enough in either of its demographics to make up for the cost of making it. And considering that the western vocaloid market is smaller than the eastern market I’m not hopeful that a vocaloid movie would sell well here.

Sixth issue: Budget. Let’s be real a project like this wouldn’t be given a working budget and lots of people would have to work overtime to make this a functional product. I really don’t want that to happen to my projects even if the animation is being done by a different studio.

Seventh issue: The AI debate. Vocaloid and other vocal synthesizer softwares are often confused for Ai products instead of instruments. Many people would boycott the project because there’s a lot of people who don’t know this is voiced by Vocal synths(an instrument that’s made pretty ethically) and not AI generated voices(unethical and lifeless). Which would add to the possibility of it not making any money at all.

I’ll reblog this again tomorrow with the plot of the plot so yall can make fanfic based off the premise.

[takoyakidonuts]

Futaba Minato Talk Releases on CeVIO AI and VoiSona!

Today marks the release of Futaba Minato Talk on both CeVIO AI and VoiSona Talk! CeVIO AI Futaba Minato Talk Offical Demo After months of development, Minato finally leaps onto both engines and is free on VoiSona Talk for users who have purchased her new bank on CeVIO AI! She’s currently on sale for 10% off on DLsite as well, normally starting at 8,778 yen digitally and 10,120 yen physically…

[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.

[menkawata]

sweet talk

[dreadark]

wanted to make some long post talking about vocaloid and AI voice covers but then I realized I don't want to be that coherent so here's a disorganized rant

vocaloid uses AI. stop saying it doesn't. what's even the point of this you can literally google it man

so do synthv and cevio and etc

this is okay because the usage of AI isn't inherently bad is this a hot take...? you know AI is used in medical tech right? do any of you guys know what AI actually means??

but AI voice covers have 2 main problems, one is of course that someone's voice is being used without their permission

(and the real danger here is deepfakes, which should be obvious, but I'm talking about vocaloid here so...)

the other, which I think most people don't realize, is that someone else's singing is also being ripped off like... AI can't figure out how to sing a song. it just makes an approximation of the voice it was trained on sound like something that already exists for AI covers of vocaloid songs specifically this means they're definitely ripping off a utaite cover, and you can bet the uploaders won't mention who...

this is why vocaloid takes more effort, the person tuning the vocaloid has to decide how it will sing each note newer AI vocal synths do some of this automatically but by assuming what would sound natural (roughly) (and with mixed results), not by ripping off someone else who already sang the song

which is why people call vocaloid an instrument. it's a digital instrument. you have to decide what notes to play

so please stop trying to argue AI is bad just because it makes things too easy like are you going to argue against digital art next?? there's 100 other valid arguments why this

why did I make this bullet points and then talk in sentences...

[justanie]

It's been a while since I made a post like this...and it's probably the worst case scenario to talk about now. No, I love GUMI and I am proud of how it is giving more attention to enter into multifacets for different voice banks...I clarify this, it is NOT made to defame GUMI SV or Internet Co of this decision. My problem is due to SynthV and its scandalous Fandom that...I am not pleased with the level of stability that most users have for this type of news.

Well, I won't deny that Vocaloid is currently in decline and barely had the luck to update V6 a year ago, but it's not to say that they have always been terrible at their job and that they spread evil just because they use a more complex level to make new voice banks. Let's remember that if it weren't for Vocaloid, other Synthesizers like UTAU and SynthV itself would not exist, yes, their main star Miku and company are no longer updating themselves with all this success that the most recent synthesizers have but I remind you that, in 2019 Crypton had decided this after the decline of V5 and how Yamaha has become a conflictive company that lost all ties of labor cooperation to continue updating their Loids. So if there is someone they want to blame, it is both companies for having a closed mind, do not defame and make the Vocaloid characters look bad for this very reason.

Now the SynthV Fandom...look, I'm not one of those people who prejudge and make a group of people look bad just because I don't agree with their opinion, in certain cases, I admit that SynthV has surprised me and certain banks I like the voices of it depending on the cover I hear. But the direction I'm seeing from the majority of fans gives me a bad taste in my mouth...instead of taking things calmly, they exaggerate by saying that Teto or Gumi SV is the best thing that ever happened in SynthV and that it's going to trample to Vocaloid only because they consider their banks better due to the inclusion of AIs and the realistic intonation they choose (In case someone forgets, remember that before this happened many considered Gumi's voice to be more realistic even if it was already from Vocaloid). No vocal synthesizer is going to be superior to another, what's more, if you are a fan of Stardust or Sora, you will know that they managed to please a number of fans in a healthy way, so why is there this hype with Teto and Gumi? Easy, SynthV fans are demanding iconic character voices to take on Vocaloid, because "Vocaloid is so horrible and bad that it didn't leave its Synthesizers free to update" I remind you, Vocaloid is not a single company, there are several those who work using this program so it is ridiculous to judge an entire program when they are executives and people who work on the decision of their Vocaloids, as I said before, do not look down on the voices and the program itself.

And my last point which would be the controversial one...the AI and the supposed realism that people ask for in Vocaloid. Fans of yesteryear will know that the essence of Vocaloid was always that of "a robotic voice that is programmed to sing." At what point did they ignore what it characterized Vocaloid? The thing is that with the advancement of AIs, people have forgotten that same meaning that Vocaloid represented, I see that SynthV is taking advantage of the use of these and that is why people ask for more, not only original voices of it, but they demand the extinction of Vocaloid so that its popular voices belong to them. This is not like in animation companies where one is buying and acquiring the products of another, like a certain company that is also being hated, the voice bank programs are free, even if Yamaha Corporation has the authorization of Vocaloid or in more cases variables, AH Software has authorization from Voiceroid, it is enough to do business with them so that Vocaloid can be distributed to other companies and so that they also have the decision to use SynthV or Cevio for their voice banks.

I'm not claiming which side is better, I'm just asking that there stop being wars and insinuations over these issues that Gumi has been suffering from being a prisoner of Vocaloid, GUMI was originally from it, what Internet Co does is give it more variety of programs ( which not only SynthV, we will probably see a Cevio GUMI in the future) and believe me this is not the first time this has happened, in this case it was distinguished by being a Vocaloid with variable banks and intonations. Speaking of the latter, I remind you that the program works depending on how it is used, yes, I see people complain that the banks they have are complex, but even with that, there are still people who are planning to use Vocaloid because they have brief experience and knowing the proper use for when a bank will be used, I'm also not saying that only Vocaloid experts are the only ones who can handle it, anyone can be capable, it just takes a real intention to use it as it should and not be bothered by it.

You can ignore my opinion if you don't like me or you're not interested, I know that many won't think the same as me, but keep in mind that if you continue with that disastrous attitude of "Vocaloid deserves to die" it won't amount to anything because that the general fandom of the Vocal Synths can be better than the reputation that SynthV is having and the defamation they give to Vocaloid, which was the one who started this trend of robotic idols that sing as I mentioned before. And seeing people asking for "realism" makes lose why Vocaloid should exist in the first place...