ClipboardI….png - 43.27 KB (1036x234)

vipchan pls

>>21485
Your utau probably needs to be somewhat popular to get in. Riko's relatively underground and no one outside this site knows her so i doubt she'd make it. Plus there's the whole thing about her being a pee obsessed schizo, she'd have to get the Tei treatment to end up on a commercial engine.

>April 1st
either they chose the worst date possible or it's nothing

https://youtube.com/watch?v=g0iUVsxfv_4

>>21488
>>21486
This has existed for a while and it's mostly random friends of the devs

>>21486
Everyone says this about Tori but Ritsu is arguably more edgy and he's on every commercial engine ever

What exactly makes this software any different than UTAU other than the UI being more akin to V6?

>>21490
Tori isn't even meant to be edgy, just eccentric.

>>21488
Nah its real

So ... UTAU with a modern UI?

>>21611
i think its supposed to be like early vocaloid but it just happesn to have utau compatibility

>>21613
They made a blog post where they basically try to sell it as a user-friendly UTAU alternative. It does have its own engine though.
https://blog.expressivelabs.net/build-the-future-of-singing-synthesis-with-us/

>>21617
Nice. With this, Tunelab and OpenUTAU producers have no excuse not to use UTAU now.

>>21618
i think utau already is more popular than it was 10 years ago, people like iyowa have been using it

>>21618
Don't forget SynthU, which is being made by the original creator of UTAU
But it is unknown what happened to it or if its still being developed

Since Mikoto supports AI voicebanks have they said anything about DiffSinger support?

>>21621
don't think so

I'm just wondering whether the crowdfund will work out. Maghni got 43k, and this is asking for 35k...

>>21623
Samefag but I'm dumb and didn't realize it was euros. They're pretty much asking for the same amount then.

https://youtube.com/watch?v=5LIC8r9zf0U

>>21623
The WVF ain't having that shit anymore after what happened to Maghni

The current Maghni team isn't to blame for the failure of the project.

>>21611
From what i understand its utau but easier to use and with its own resampler

I'm still sad about maghni

>>21484
All cases of imported UTAU voicebanks onto this synth I've seen make them sound worse, if anything. You'd be better off using regular UTAU

>>21824
I already use UTAU with HiFiSampler and it sounds the same as Vocaloid did during its glory days

>>21826
Exactly, so what's the incentive from Mikoto (besides UI)? I hope the engine has improved since their UTAU Day demos when they release the trial

>>21827
>trial
are they making this a paid thing

ClipboardI….png - 32.57 KB (1266x169)

>>21828
In their FAQ, plus the fact that a trial is coming April 1st

>>21829
>Paid UTAU
No thanks

Eh i dont know what this is but i'd prefer if maghni released. We're never getting that oliver voicebank.

>>21827
Supposedly they've posted demos of an AI engine on their dicksword

Campaign went live
https://www.indiegogo.com/en/projects/expressivelabs/mikoto-studio

>>22140
Sounds like a more robotic DiffSinger (still somehow better than V6)

>>22140
People in this thread made it sound like it was going to be worse but honestly its not really that bad

>>22140
I like it

>>21628
They’re still to blame for the active silence. People don’t think they’re entirely being honest rn either. A lot of the current team is still from the old team.

>>22235
All i want this year is an update on Maghni

>>22277
The Zero-Gloids and PowerFXloids are equally dead. A lot of people don't wanna hear this but it's time to let go of the past and accept that one of those companies is dead while the other wants nothing to do with vocal synthesis anymore.

>>22278
:(

So what do we think of Mikoto?

>>23275
It's better than i expected but I'm not sure if I'm willing to pay for what's essentially just UTAU with a better UI.

>>23275
Doesn't look too bad but i really think it should be free

>>23275
The ToU is really irresponsible and I’d even coin the term Anti-Vocaloid for it

>>23295
>Do not misrepresent our characters in any way. Examples of this include: […] Creating alternative versions of our characters. […] Do not alter the output of our products using voice changing software beyond minor edits.
That, the requirement to put copyright disclaimers on your work, and the clause in the TOS that lets them resell your uploads look pretty busted. It kind of reads like their business strategy is to capture UTAU users and put them in a walled garden.

>>23298
<you shall not create derivatives/redesigns
<you shall not mix your fucking audio
this is how this reads to me. incredibly stupid if true.

>>23299
1st one is definitely what they mean. 2nd one they specify “izotope products and Melodyne” as minor edits which is not really clear.

>>23300
>Izotope
They make software and VSTs for mixing and mastering audio (usually vocals). Vocal doubler, Ozone Imager, Nectar and RX Pro are some of the stuff they've made and that I own.
>Melodyne
An autotune software similar to NewTone but (in my opinion) better. If I had to guess it's what VocaP's use to make their vocaloids sound even more robotic. I know a lot of rappers use it.

>>23301
Yeah, I mean they seem like examples of standard vocal processing. It makes it seem like if you wanted to, like, crush/distort/chop up the vocal heavily to use as a background element in a track it’d be against TOU, which is bizarre. But I’d also imagine that would be doable through izotope products.

>>23302
I can't believe they've managed to come up with guidelines more absurd than Fukase's.

>>23302
I assume they're trying to ban RVC and stuff like that? It's worded really weirdly though

where are you guys even reading the ToU

>>23305
https://expressivelabs.net/legal/characters

tos.PNG - 24.60 KB (669x228)

What even is this? Their NSFW policy already requires the characters to be 18+. They can't be kids or teenagers ever? At all?

>>23306
Ok from what i see here you're allowed to create alt designs and outfits, you just can't change the character's age, gender, etc (so genderswaps are banned i guess?).

But what gets me the most is the rule against vocal processing, what's the point of banning that when putting effects on the vocal track is pretty much essential to make your music not sound like shit?.

Also
>Users assume full liability to hold or obtain the necessary rights to background music, instrumental tracks, additional voice library characters from other companies, and/or any elements of the work that they did not create. ExpressiveLabs will not be held responsible for the abuse of copyrights or other license rights by the user.
Does this imply you can't make covers either? Why?

>>23307
It says "unless explicitly specified" so it's technically allowed.

Some of these terms are pretty bizarre though, maybe it's a good thing Tori didn't end up on this engine.

>>23304
There is a separate clause for AI replication of the vocals.
>>23308
I assume this is a CYA for the company but it’s worded in a way that feels restrictive, especially in the context of coverers getting bogus copyright strikes as we’ve seen recently.

>>23309
I couldn't find any stated exceptions on their site. It's really bizarre, why would we have to ask for permission to upload a song set in high school?

Clearly a “we want no Zaako drama” clause that was handled poorly.

If I wanted to make a voicebank I'd rather just get it on a different engine. What's the point of making a completely new engine when there are already well established ones?
It's like we are living in the V4 era except instead of voicebank oversaturation we now have engine oversaturation. Except in this case if their TOS is way too strict it affects way more than just one character.

>>23275
The software doesn’t seem to bring anything new to the table. Their rules against vocal processing also basically prevent anyone with a stylized or robotic tuning style (me!) from using it.
This project has also realized my worst fear: VSynth companies heavily censoring people in order to appeal to the Western market. Imagine if Crypton banned reinterpretations of Miku’s character, Vocaloid culture would not exist today. I barely had interest in Mikoto prior to this too, they’re never getting a cent from me lol. I miss Maghni.

>>23315
> I miss Maghni.
I don’t honestly. Vocaloid/SynthV as commercial singing synths plus UTAU/Diffsinger as the FOSS alternatives (for robotic/realistic niches respectively) is a fine equilibrium to me.

>>23316
i think i speak for everyone when i say we wanted maghni for the pfx vocals

>>23316
>>23317
>>23315
Hard to miss Maghni when we never got it in the first place. If anything I miss my money.

>>23318
Technically it's still in dev but if they end up canceling it I hope they refund people.

>>23317
Yeah pretty much this

I only looked forward to Maghni because of Oliver and BigAL

The radio silence makes me anxious and I didn't even fund the project so I can only imagine how it must feel for those who did

my favorite part of the nsfw policy

>The following things are not allowed when depicting any of our products:
>Uncensored nudity

almost defeats the whole point of it

>>23313
The Zaako incident was the biggest nothingburger in Vocaloid history and was extremely blown of proportion by the western fandom. I'm surprised people are still bitching about it to this day.

>>23329
kek

>>23314
>It's like we are living in the V4 era except instead of voicebank oversaturation we now have engine oversaturation
Really does feel like it sometimes

>>23301
What's the point of banning VSTs? Some producers use autotune/Melodyne as an artistic choice for example. It's just silly to not let people use them.

>>23322
With what money? They used up all the funds. They were supposed to deliver some rewards back in December 2024. When the first delay came we expected everything to have come by now but instead they’re sending everything out 1 order at a time sporadically and ghosting anyone wanting a status update. I quite literally don’t expect it to come out anymore.

Sorry to be so heated but this whole situation is exactly why I’m not backing Mikoto. Aside from the fact they’re a start up, I have no confidence in western engine projects anymore.

>>23750
Same here plus the oversaturation in synths doesn't help

>>23758
Right now the best synths for English are Vocaloid and SynthV, maybe UTAU too but barely anyone uses it

Early access preview is out
https://mikoto.studio/eap

>>23815
I get the feeling that not a lot of people will use this

made a comparison using toriko cv, first is mikoto, second is open utau with moresampler

>>23817
Moresampler is noisier but sounds better

>>23306
The rules are not as bad as people here are making them out to be, the issue is that they're worded in the worst way possible.

>Do not alter the output of our products using voice changing software beyond minor edits. Minor edits include pitch correction, filtering, the use of vocoders, or any edits made possible by dedicated voice processing audio effects (i.e. iZotope Nectar, Melodyne, et cetera).
You can use Melodyne or Izotope to process the vocals, it's included under "Minor edits".
It does seem like creating 'genderbent' versions of the characters is prohibited (unless they go out and clarify this) but creating alt designs or MV characters isn't against their TOS.

>>23943
Regardless though i'd still be wary of any vocal synths that aren't from Japan or China at this point

>>23944
Korea has Vox Factory and it seems to have otaku as the target audience

bugfix dropped

>>21484
I misread the OP as "Singing synthesizer by ElevenLabs" and thought the "I'm sorry but I can't fulfill this request" guys were making a vocal synth.

i cannot f….mp4 - 799.64 KB (640x360)

>>24683
Lol. Trying to make a song with the ElevenLabs vocal-synth would feel like this.

Now that the dust has settled what is /leek/'s veredict on Mikoto

>>25773
I mean it's alright. I don't see myself using it over OpenUTAU and there's definitely room for improvement but overall a lot of the problems mentioned ITT are overstated and Mikoto's just an okay vsynth.

The campaign has finished
"Project was not funded
The project didn't meet its goal.
No funds were collected from backers.
The campaign ended on 5/15/2026.
56 backers pledged €18,197
This is 51.99% of the €35,000 goal."

>>25956
What does this mean for Mikoto

>>25958
>"this isn’t the end of Mikoto Studio. We are still 100% committed to bringing our singing synthesizer to life. The campaign might not have gone our way, but the dream is very much alive. The only difference is that it’s just going to take us a little longer than we originally planned. We’ll be sure to keep you updated as the development continues."

>Right now, though, our small team is going to take a short 2 week break to rest, reflect, and recharge after the intensity of the campaign. We’ve poured everything into this, and we believe coming back with fresh energy is the best thing we can do for the project."

Also this:
>"mikoto 0.5.5 is still coming before our 2 week break, stay tuned for that"

>>25962
Interesting

>>23817
She sounds better in Mikoto Studio but it bothers me that her voice just cuts off like that

Honestly they just should have never did a crowdfund. It was doomed to fail. Hopefully they make do with this back up plan though.

>>25978
Is it because western studio? I noticed JP crowdfunds get funded within hours if not minutes

>>25994
I don't think so, western fans have been crowdfunding stuff for a while. Mikoto's problem was that they only really marketed to overseas UTAU users. That part of the fandom isn't big enough to carry a 30k crowdfund.

>>25998
Imo it was because their thing was that it's an "easy alternative" to utau, which doesn't hold when you market to people that grew up on it, and when OpenUtau offers the same functionality, but it's free. They should have marketed to people that are new to vocal synthesis.

>>26000
Someone should make a sample based vocal-synth. I know that AI has made the demand for those lower and that UTAU exists but I don't think it'd do too badly.

>>26001
There's kinda no need for one honestly. UTAU already exists and has an infinite library of free voicebanks and with resamplers you can improve their quality. Best part is that its free.

>>26003
Yeah i agree, OpenUTAU with MoreSampler and HiFiSampler is all you really need these days. For voicebanks you can just pick a voicebank that's recorded in decent quality.

>>23817
Sounds less metallic than moresampler but the cutoff is weird

>>25998
>>26000
These plus the fact lingering factors from Maghni not having come out yet as well as the fact they were not marketing to professionals properly. In the west you NEED the support of professionals.

Not to mention, none of the JP crowdfunds were necessarily for new engines either. They were for voicebanks for existing ones, so it’s not necessarily a fair comparison.

>>26057
Adding on again: this is also their very first product. They are a new company. By comparison VocaTone at least had Oliver and Yohio on Vocaloid so people had the impression of deliverability. Of course sentiment in that regard changed but during the campaign, having something delivered was better than nothing.

>>26058
They also had Big AL, Sweet Ann and RUBY/RVBY. All of which were teased...and then all we got was a RVBY demo

>>26057
>In the west you NEED the support of professionals
FWIW, Maghni hit their crowdfund goal back when all of their promos were targeting the fandom. I could see Mikoto being funded if they had more big names attached to the project.

>>26061
This and the fact that they promised AI versions of those old voicebanks which are stuck in V2-3. AFAIK V6 is no longer compatible with V1-V2 and chances are they'll drop support for V3 by the time V7 is out.

Meika Mikoto Studio

>>26061
This is not entirely accurate. If you look a bit deeper, they had backing from universities and showed Maghni’s development off at in person events. The goal for Maghni was also less than Mikoto’s. There was more motivation after they reached the goal, but Maghni had attracted professional attention despite its appearance.

>>26063
As long as V5 is supported, v3 should be supported. I don’t think we’ll have to worry about support ending as much as we’ll have to worry about Maghni being in dev hell.

>>26105
They did kill V2 support though didn't they? Voicebanks like Big AL and Sweet Ann never got an update.

>>26106
Yes, but they killed it off halfway through V4. If V3 support was gonna end, they would’ve done it years ago. Not to mention, they re-added and added features for V3-V5 banks in V6 like XSY and direct pitch. We’ll see more V3 banks discontinue before they end support.

>>26106
Thank god for tunelab

So what happened to this project?

>>26106
It's really disappointing that if you own anything newer than V4 you basically can't use them and have to resort to either buying an older version of Vocaloid or Tunelab pirate plugins.

>>30091
On hiatus apparently, idk if their dicksword has anything more specific

>>30095
You can replace the files of a V6 compatible bank and it'll work but at that point I'd just use Tunelab

>>30105
To be honest, i don't know why they thought making a paid version of UTAU was going to work
I want western vocal synths to succeed but so far only Maghni brings something new to the table and even that failed

>>30227
I wouldn't say it has failed YET but its future isn't looking too bright

>>30240
They said they're still gonna finish it at least just slower

Not to necro but I just wanna complain somewhere. Approached them, had a meeting, and was looking forward to developing a line of voices as their tech seemed promising. I had a plan and character documents etc ready, but after the initial talks (which I believe went well!), I got totally ghosted. After multiple attempts to get some clarity on the sudden lack of communication, I still got nothing. It's just... lame. Really lame. "Wtf" really, you don't just do that. You could have said anything, or even told me you were reconsidering, but just complete silence? Unprofessional af..

>>32460
Why is it that all the vocalsynth companies here seem really unprofessional? Maghni's the only one I kinda trusted due to their association with Vocatone and look how that turned out.

>>32462
> vocalsynth companies
Makes me wonder if the server they all congregate in is an echochamber of sorts. I'm not optimistic for newcomers in the commercial scene (if you can even call it that).

Also, Mikoto's AI is basically Diffsinger (they even use the diffsinger format). Also, their NEST engine is similar to Vocaloid's concat engine, but I'm preferential to Vocaloid. If one just wanted to sell their own line of voices, professionally recorded and without insane licensing fees (Mikoto's was fair, I'll give them that), just stick to Diffsinger and UTAU. I know some people get flack for commercial voices, but Mikoto at present doesn't offer anything to the experienced vocal synth user.

TBH, Mikoto as a software suite is marketed towards those who aren't experienced with vocal synths but still want to get into it.

>>32464
>Also, Mikoto's AI is basically Diffsinger (they even use the diffsinger format).
??

>32465
Partial mistake here, they use the same methods as diffsinger for *data annotation*. As for synthesis, I can't make definitive comments. Sorry about that.

>>22277
Anon... I...

>>32481
monkey's paw strikes again

>>22277
I'm sorry anon

>>32464
There are outliers, but most of the companies that have a lot of these problems tend to be Western ones.

The Eastern side of things has its hiccups, but those happen much less by comparison. I swear almost every Western company has some sort of issues going on behind the scenes.

At the very least, I hope these recent failures actually become learning experiences.

>>32506
What western vocal synth company hasn't fumbled though?
>inb4 Eclipsed Sounds
Referring to companies that have made their own vocal synth engines here

>>32466
I think ENUNU uses the same method so it's not a DiffSinger thing. I'd go as far as to say that most AI vocal synth labeling probably follows a similar process if not the exact one.

>>32507
Pompeu Fabra University

>>32462
The broader issue is that most businesspeople in the west don't have a good grasp of otaku culture, nor do they see it as worth the effort. Meanwhile, the people who really want to make vocal synths are all fresh college grad programmers and artists who haven't been in the corporate world. There's a lot of basic practical knowledge that isn't being taught here because the overlap is so small.

>>32570
You hit the nail on the head

>>21485
If they ever release a commercial voicebank it's not gonna be on a western engine. Just saying.