No.21484[Last 50 Posts]
A new singing synthesizer by ExpressiveLabs that claims to be easy to use and compatible with UTAU voicebanks. The crowdfunding campaign starts on April 1st.
https://x.com/expressivelabs/status/2036956525223113012https://mikoto.studio/crowdfund<Can i become a voice provider?Yis...
https://expressivelabs.net/talent No.21486
>>21485Your 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.
No.21488
>April 1st
either they chose the worst date possible or it's nothing
No.21490
>>21486Everyone says this about Tori but Ritsu is arguably more edgy and he's on every commercial engine ever
No.21506
What exactly makes this software any different than UTAU other than the UI being more akin to V6?
>>21490Tori isn't even meant to be edgy, just eccentric.
No.21611
So ... UTAU with a modern UI?
No.21613
>>21611i think its supposed to be like early vocaloid but it just happesn to have utau compatibility
No.21617
>>21613They 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/ No.21618
>>21617Nice. With this, Tunelab and OpenUTAU producers have no excuse not to use UTAU now.
No.21619
>>21618i think utau already is more popular than it was 10 years ago, people like iyowa have been using it
No.21620
>>21618Don'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
No.21621
Since Mikoto supports AI voicebanks have they said anything about DiffSinger support?
No.21623
I'm just wondering whether the crowdfund will work out. Maghni got 43k, and this is asking for 35k...
No.21624
>>21623Samefag but I'm dumb and didn't realize it was euros. They're pretty much asking for the same amount then.
No.21628
The current Maghni team isn't to blame for the failure of the project.
No.21630
>>21611From what i understand its utau but easier to use and with its own resampler
No.21632
I'm still sad about maghni
No.21824
>>21484All 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
No.21826
>>21824I already use UTAU with HiFiSampler and it sounds the same as Vocaloid did during its glory days
No.21827
>>21826Exactly, 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
No.21828
>>21827>trialare they making this a paid thing
No.21830
>>21829>Paid UTAUNo thanks
No.21833
Eh i dont know what this is but i'd prefer if maghni released. We're never getting that oliver voicebank.
No.21847
>>21827Supposedly they've posted demos of an AI engine on their dicksword
No.22144
>>22140Sounds like a more robotic DiffSinger
(still somehow better than V6) No.22152
>>22140People in this thread made it sound like it was going to be worse but honestly its not really that bad
No.22235
>>21628They’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.
No.22277
>>22235All i want this year is an update on Maghni
No.22278
>>22277The 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.
No.23275
So what do we think of Mikoto?
No.23281
>>23275It'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.
No.23286
>>23275Doesn't look too bad but i really think it should be free
No.23295
>>23275The ToU is really irresponsible and I’d even coin the term Anti-Vocaloid for it
No.23298
>>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.
No.23299
>>23298<you shall not create derivatives/redesigns<you shall not mix your fucking audiothis is how this reads to me. incredibly stupid if true.
No.23300
>>232991st one is definitely what they mean. 2nd one they specify “izotope products and Melodyne” as minor edits which is not really clear.
No.23301
>>23300>IzotopeThey 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.
>MelodyneAn 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.
No.23302
>>23301Yeah, 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.
No.23303
>>23302I can't believe they've managed to come up with guidelines more absurd than Fukase's.
No.23304
>>23302I assume they're trying to ban RVC and stuff like that? It's worded really weirdly though
No.23305
where are you guys even reading the ToU
No.23308
>>23306Ok 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?
No.23309
>>23307It 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.
No.23310
>>23304There is a separate clause for AI replication of the vocals.
>>23308I 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.
No.23312
>>23309I 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?
No.23313
Clearly a “we want no Zaako drama” clause that was handled poorly.
No.23314
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.
No.23315
>>23275The 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.
No.23316
>>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.
No.23317
>>23316i think i speak for everyone when i say we wanted maghni for the pfx vocals
No.23318
>>23316>>23317>>23315Hard to miss Maghni when we never got it in the first place. If anything I miss my money.
No.23322
>>23318Technically it's still in dev but if they end up canceling it I hope they refund people.
No.23326
>>23317Yeah 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
No.23329
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
No.23332
>>23313The 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.
No.23339
>>23314>It's like we are living in the V4 era except instead of voicebank oversaturation we now have engine oversaturationReally does feel like it sometimes
No.23720
>>23301What'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.
No.23750
>>23322With 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.
No.23758
>>23750Same here plus the oversaturation in synths doesn't help
No.23759
>>23758Right now the best synths for English are Vocaloid and SynthV, maybe UTAU too but barely anyone uses it
No.23815
Early access preview is out
https://mikoto.studio/eap No.23816
>>23815I get the feeling that not a lot of people will use this
No.23818
>>23817Moresampler is noisier but sounds better
No.23943
>>23306The 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.
No.23944
>>23943Regardless though i'd still be wary of any vocal synths that aren't from Japan or China at this point
No.24059
>>23944Korea has Vox Factory and it seems to have otaku as the target audience
No.24115
bugfix dropped
No.24683
>>21484I 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.
No.25773
Now that the dust has settled what is /leek/'s veredict on Mikoto
No.25774
>>25773I 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.
No.25956
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."
No.25958
>>25956What does this mean for Mikoto
No.25962
>>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" No.25970
>>23817She sounds better in Mikoto Studio but it bothers me that her voice just cuts off like that
No.25978
Honestly they just should have never did a crowdfund. It was doomed to fail. Hopefully they make do with this back up plan though.
No.25994
>>25978Is it because western studio? I noticed JP crowdfunds get funded within hours if not minutes
No.25998
>>25994I 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.
No.26000
>>25998Imo 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.
No.26001
>>26000Someone 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.
No.26003
>>26001There'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.
No.26011
>>26003Yeah 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.
No.26020
>>23817Sounds less metallic than moresampler but the cutoff is weird
No.26057
>>25998>>26000These 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.
No.26058
>>26057Adding 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.
No.26060
>>26058They also had Big AL, Sweet Ann and RUBY/RVBY. All of which were teased...and then all we got was a RVBY demo
No.26061
>>26057>In the west you NEED the support of professionalsFWIW, 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.
No.26063
>>26061This 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.
No.26092
Meika Mikoto Studio
No.26103
>>26061This 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.
No.26105
>>26063As 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.
No.26106
>>26105They did kill V2 support though didn't they? Voicebanks like Big AL and Sweet Ann never got an update.
No.26110
>>26106Yes, 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.
No.29843
>>26106Thank god for tunelab
No.30091
So what happened to this project?
No.30095
>>26106It'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.
No.30105
>>30091On hiatus apparently, idk if their dicksword has anything more specific
No.30226
>>30095You can replace the files of a V6 compatible bank and it'll work but at that point I'd just use Tunelab
No.30227
>>30105To 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
No.30240
>>30227I wouldn't say it has failed YET but its future isn't looking too bright
No.30242
>>30240They said they're still gonna finish it at least just slower
No.32460
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..
No.32462
>>32460Why 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.
No.32464
>>32462> vocalsynth companiesMakes 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.
No.32465
>>32464>Also, Mikoto's AI is basically Diffsinger (they even use the diffsinger format).??
No.32466
>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.
No.32486
>>32481monkey's paw strikes again
No.32506
>>32464There 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.
No.32507
>>32506What western vocal synth company hasn't fumbled though?
>inb4 Eclipsed SoundsReferring to companies that have made their own vocal synth engines here
No.32515
>>32466I 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.
No.32564
>>32507Pompeu Fabra University
No.32570
>>32462The 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.
No.32582
>>32570You hit the nail on the head
No.32594
>>21485If they ever release a commercial voicebank it's not gonna be on a western engine. Just saying.