#VoiSona Talk

[mi-soni]

Tanaka San☂️

[takoyakidonuts]

A.I. Voice 2 Unoka Officially Releases! + A.I. Voice 2 Likea Announced! + IA 13th & ONE 10th Anniversary Stream Reveals Major VOCALOID6 and VoiSona Talk News!

After a long wait, Unoka has officially released onto AI Voice 2! AI Voice 2 Unoka Official Product Image Available digital only for 12,980 yen including tax, Unoka’s new talk bank boasts the “Calm���, “Joy”, “Anger”, and “Sadness” expressions as well as “Shizuku” based on her additional bank from her AI Voice (1) package. Anyone looking to pick her up can check out the links…

[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

[bmpmp3]

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

[red-moon-at-night]

POV: one of your favourite vocaloid cover artists is getting a vocal synth made with her voice

(it's oktavia and the synth is called SELENA and im going to CRY AAAAAAAA)

(also obligatory link to video with the vocal demo:)

[late-night-vocaloid]

I wanna ask a fun question. rb and put your favorite vocal synth in terms of voice, your favorite in terms of design, and your favorite overall in the tags, and feel free to elaborate

[mayuofficial]

am i ever going to get updated?

[em-um-canto]

I got into vocaloid in the early 2010s and it was a amazing time with new songs and amazing voicebanks coming out

Eventually i drifted away and only around 2021-ish i got into vocaloid again and...

There are still great songs being made! But somehow it feels like it's being overshadowed by the Iconography of Hatsune Miku

does anyone like vocaloid songs nowadays … or is it just miku fanart and proseka fans … pls i need to talk to someone about my favourite vocaloid songs ….

[meerkatp]

OKAY, so computer update.

I just got it back. (First time I got hardware sent back after sending it in I'll be damned.) At the moment everything seems to be in order but I just don't know how stable it actually is right now. Like, right now it's reading both SSD drives as separate drives (instead of only one of them, or the shitty way it was set up before as one 4TB drive) but considering how before it did read them as two drives, after turning it off and on again, it would then only read one. I did turn it off and on again now and it's still reading both of them but if that's gonna last I don't know.

If it's still working tomorrow I think I'll start reinstalling some of my VOCALOIDs, but as a trial. I might install CeVIO, VoiSona, Piapro Studio NT, and FL Studio since those licenses either carryover easily (CeVIO can easily move authorization every 24 hours and the rest are tied to accounts. Would be better if there was no DRM at all though.) but aside from those last four, I'm not going to activate anyone to be safe.

My ask box will still remain closed for the time being but I can actually talk to people now. I'm not going to open it untill I'm sure my computer's in working order.

[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.

[synthsatellite]

Additionally, IA and ONE's VoiSona Talk will be released today

Details here

[takoyakidonuts]

Soyogi Soyogi's Upcoming CeVIO AI Release to Include VoiSona Versions!

After a massively successful Crowdfunding campaign and many months, Soyogi Soyogi is expected to be released on CeVIO AI this month! While the final release date is yet to be set, they have officially revealed that Soyogi will also be launching on VoiSona as well on the same day! Official VoiSona Soyogi Soyogi announcement image from soyogi-fractal.com Both his song and talk banks will be…

[vocalsynthbdays]

happy (late) birthday futaba minato(cevio ai), shiteyan'yo(fanloid), fione(utau), and kaikai kim(utau) !!!!! [feb 2]

(minato)

(shiteyanyo)

(fione)

(kaikai)

Futaba Minato is a japanese synth developed by Gasoline Alley Inc., and originially released on 2 dec 2022. shes voiced by Sachika Misawa and illustrated by hitoba. after her initial cevio ai release, minato was released for voisona on 18 aug 2023, and cevio ai talk on 26 jan 2024. minatos character birthday is feb 2

shiteyan'yo is a super deformed mascot(an exaggeration or parody of an exisitng synth) fanloid created in 2010 by Ryūse/ puzzle157xxx, who originally drew her. she has been officially recognised by crypton and features in some pjdiva games. she is often grouped with larval Rin and calne ca as "nightmare fuel" mascots. shiteyanyo is (obviously) based on Hatsune Miku

Fione (Fιφne) is a japanese synth released on 4 june 2020. she is voiced and illustrated by arusechika/ aruseee. fiones character birthday is feb 2

kaikai kim is a japanese synth released in 2011. she is voiced and illustrated by KaiSuki

[irunabara]

TechnoSpeech's mascot, Tanaka San-chan (San is not an honorific) will become a voice for VoiSona Talk!

She is 26 years old, 156cm, and 46kg. She was born in Nagoya on November 19th and her favorite foods are hitsumabushi and ogura toast.

San is a employed by vocalsynth manufacturer and an ever-smiling public relations worker. She's very serious and sensible on-duty. She collects and even hand-makes parasols and umbrellas, having special umbrellas for weather, enjoyment, and battle. She has a devilishly strong grip.

[bmpmp3]

and please dreamtonics or any third part synthv dev anyone i am BEGGING you to make more english synths with non-american accents i dont mind the americans but i am GREEDY and i want MORE

[necronatural]

Why the fuck would you assume a research field that has been chugging along for like 60 years would not maintain libraries of public domain voice data.

It is, in fact, a very interesting topic! Voice rendering research has been overwhelmingly dominated by English and Japanese speakers, so these are the largest data pools. Because these are sourced from donations, it's full of wildly disparate recording environments with wildly disparate speech quality. FirstVoices has volunteer audios specifically recorded for FirstVoices that has that same recording jank.

So Vocaloid as software directly has its roots in this research, which is why it's historically been full of weird obsessive nerds. At no point has anyone with a modicum of common fucking sense went "modern TTS voices are evil fucking AI slop and you're a bootlicker if you use it" because we have brains and are aware of this long history of voice synthesis development. We can assume this is the natural evolution of technology, using resources accrued over a massive amount of time, and unrelated to the devastating escalation capitalist interest is imposing on computer learning in the current era.

If you gave a fuck, you'd be asking 'how has capitalism pissed in your pool'? Well. I actually put universities as the provider in this photoset specifically because they do in fact be pissing; after the AI boom, groups would collect/record data and sell this for a galling amount of money.

It's obvious the profit-seeking of data distribution would lean to swaths of stolen data, and also obvious business techbros trying to leapfrog off the AI bubble are going to buy whatever is on offer to get a competitive product out, and that big conglomerates like Google or Microsoft are motivated to make Superdata packs to crowd out the market, because capitalism. Swear on my life services like Character.AI have got to be stuffed sick with gluts of stolen audio. However, I'm talking about Synthesizer V, a program that long predates the AI boom and is headed by its own programmer. Cevio/Voisona and Vocaloid are similarly software that predates that boom. We can assume... I am not talking about AI profiteering here!

A lot of people try to explain this without knowing anything about how voice synthesis works, so here's my breakdown on No, Hatsune Miku Is Not AI, And No, AI Voice Synthesis Is Not Bad.