>>21967 (me)
I mean a vocal synth software, not a voicebank

Ask Kanru Hua. I would guess hard.

Ask that QueueSevenM guy on Kissu

Does it even need to be specifically that? Since at bare minimum any music software and carefully arranged and edited audio files can be made into vocals. Also depends do you want the whole thing from scratch or just make a front end GUI to a backend software? Im no programmer though but did a little beginner stuff in past.

I’ve been interested in doing this myself too but I know Jack about code lol

Honestly trying to make a UI for an existing engine like UTAU or DiffSinger probably is good start for practice, then you can prob move into making your own.

Iirc SynthV used Moresampler as a base(?)

>>21983
>SynthV used Moresampler as a base
huh?

>>21986
Kanru made moresampler.

>>21990
Thought you were saying SV was built on top of the code for Moresampler

If I recall correctly, SynthV was re-built from scratch 5 times, and that’s why it’s V. Probably Moresampler was used for the first version. Honestly I think the auto-tuning in SynthV is more important than the audio quality though.

10194.png - 31.30 KB (600x600)

Don't ask them

>>21995
I'm still upset

>>21994
I thought the V just stood for Vocal not roman numeral 5. Do people in Japan even use roman numerals that often?

>>21998
He was in America for a while, or at least Moresampler’s hosting situation would suggest that. It was on a university website I think

>>21998
Fun fact, SynthV is a really clunky name in Japanese. Iirc AHS didn't like it.

>>22013
Too bad even before Kanru took over the name was already solidified as a brand

>>22013
Well what do they call it

>>22017
They use the English abbreviations, but it's like "shinsebui" or "esubui", which doesn't roll off the tongue like "vocalo"

>>21983
I think it'd be funny if we could make a Vocal synth but to be honest it feels like there's an oversaturation of synths right now: Vocaloid, SynthV, UTAU, Voisona, Cevio, ACE, VOX Factory, Maghni, Mikoto, etc.

Also no one here knows how to train a DiffSinger so I doubt anyone here would know how to code a vsynth from scratch.

>>22711
On second thought, Maghni probably isn't even coming out so you can take it off the loooong list of synths, but even then there's still more I haven't named.

>>22711
Oversaturation aside, there isn't really a niche market we could target if we were to make a synth. ACE, UTAU and Mikoto already cover community made 'loids, Maghni (if it comes out) covers the PFX ENGloids and SV, VoiSona and Vocaloid cover everything else.

>>22728
ACE is for AIbros

>>22737
and the chinese

>>22728
Maybe mobile users? Yeah open utau is available on android, but not iOS.

>>22728
Doing it for fun is also allowed

>>22746
Being a mobile producer sounds painful. There are no good DAWs on iOS/Android.

>>22748
Seconding this. Can do it just for the sake of doing it.

>>22771
I'm not against it but there's so many synths no one uses these days

I should mention there is not much point unless you do something unique like a new type of vocal synthesis method, a way to control it live or a lot of automated processes that make producing easier and without locking down creativity.

>>22801
This

>>22801
Yeah, there's no point in making a vocal synth unless it brings something new to the table. I think an AI powered synth like SynthV with the same quality but free would be a game changer but at the same time DiffSinger exists.

>>22812
NEUTRINO also exists. I have mixed feelings on the machine learning "AI" synthesis method. While I like some realistic vocals if unique but I still also like the unique sound of older methods being akin to autotune, vocoder and talkbox being their own sounds.

>>22818
There was a thread on this board about how sample based synthesizers are dying in favor of AI ones. However i think that Mikoto Studio engine that's coming out soon is a non AI engine.

>>22821
Hate to break it to you but Mikoto uses AI too. It does support UTAU banks though and will likely have its own non-AI voicebanks built in.

>>21967
If you make a new synth make it sample based because there's an oversaturation of AI synths

>>21983
Idk why but this post reminded me that some company was making a vsynth but the UI was entirely vibecoded so they had to redo it from scratch lol. Forgot which engine it was.

UTAU already covers the sample based voicebank niche and SV covers the AI stuff.

What would you add to your synth to make it unique?.

>>26888
Probably XSY but I mean... UTAU V already covers that

>>26888
I’d make a synth that’s a clutch for people who can’t sing. Think synthesizer V and vocaflex, but one package. With multiple languages support and also different accents for the English vocals (you can make yourself sound Australian for example)

Another idea is more gimmicky, but maybe a software for AI virtual vtubers, but with focus on singing that also takes care of lipsync.

And a really bad idea, but maybe cloud-based vsynth that’s the same as any other BUT with a gacha for voicebanks. There would be limited time voicebanks too for max FOMO.

>>26895
You're giving bad people good ideas with that last one

>>26895
>Gacha vocalsynth
Anon if this ever becomes a thing it'll be your fault and I'll hate you forever

>>22737
ACE isn't that bad honestly, its just that their pandering to AIbros ruined their rep

>>26895
>Think synthesizer V and vocaflex, but one package
There's already DiffSinger and RVC, both of which are free

>>22023
What about Shinsego?

Come to think about it there aren't many western vocal synths besides Maghni, Mikoto and possibly some of the VST based synths, right?

>>27150
UTAU is mostly popular over here but it's made by a Japanese dude so I don't count it

>>27151
UTAU IS popular in Japan. It's only niche among producers.

Someone should grab that idea of a Western Otaku TTS and make it real. But ideally as an indie non profit project.

Just watched this, it gave me a new understanding of the purpose of VXB, but leaving here since they do essentially as for a call to developers, so if anyone does decide to make their own vocal synth, I would probably take away a few things from it.

Specifically, it's a presentation Yamaha gave yesterday about Omnivocal, which is essentially a rebranded vxb but exclusively for cubase. If anyone wants a specific idea for singing synth software, this is likely the route to go. The video should be timestamped, but if there are any issues, it's about 5 hours in.

https://youtube.com/watch?v=JqbufmjUujU [Embed]

>>27604
Seconding

Bit of a different question but what would it take to make a v-synth company like Eclipsed Sounds?

loadsamoney.gif - 2423.98 KB (480x356)

>>28018

>>28019
also developers

solaria.PNG - 227.74 KB (1283x609)

>>28019
About this much, specifically

>>28035
damn man i'm broke

>>28018
impossible unless you're a nepo or have an established fanbase willing to fund your project

3415262i.jpg - 68.33 KB (620x474)

>>28046
I could sell my house

>>28050
I'm willing to join your vocal synth company, i'll be the guy that doesn't do anything and just sits there in the background

>>28051
i'll help by drawing the characters in ms paint :)

>>28035
This is supposedly outdated. I think it’s like $60k for a SynthV bank now? Either way takes a lot of money for one person.

>>28018
I think the fee to register an llc is only a few thousand? That’s before getting into what you’re exactly making though.

>>28064
>$60k
Jesus

>>28064
Why is it so expensive anyways? Like, where does the money specifically go? I'm completely clueless on the process but I genuinely don't know how dedicating yourself to make a SynthV bank is different to any old layman putting together a Diffsinger as a passion project, with the theoretical assumption that you'll be your own voice provider etc.

>>28090
The difference is that SV is commercial

>>28064
That's for SV, right? What about Vocaloid?

>>28118
According to those fan-funded VOCALOID campaigns it seems like it costs anywhere between 3-7 million yen. (20,000 - 40,000 dollars)

>>28121
Still a lot but way less than SV

>>28118
>>28121
50k USD from what I heard. I wouldn’t use the Fanding crowdfunds as a reference point because the money is managed directly by Yamaha plus part of the funds go to manufacturing the rewards. Also handy to note some of them have the base goal guaranteed even if the campaign fails.

>>28090
It depends entirely on the agreement made. Sometimes the company will make it for you and the amount is basically equivalent to a set budget, sometimes it’s just various services to support the product. These fees can be negotiable so it ultimately comes down to what’s being agreed upon during that time. It almost is never just a straight fee payment.

>>28118
>>28121
When emailing Yamaha back in 2020, the amount I was given was 5 million yen, at the time that would have been the 50k >>28130 said. Of course since yen’s dropped the exact rate has since changed, this is also accounting for the fact that the fees could have changed again since it has been 6 years.

Across the board, fees typically range from $30k - $70k USD, I believe CeVIO/VoiSona is the cheapest but this could have changed. Unfortunately using crowdfunds as a reference point is always tricky because you have the platform fees that a portion goes to and any physical goods, so by the time you whittle it down to what’s just going to develop it, it’ll only be a fraction of what’s actually already gone into paying for development. It’s better to consider the funds being raised as raising a budget rather than raising the amount to pay the fee.

>>28132 (adding on)
Honestly you’re better off establishing some sort of notoriety or avoiding a crowdfund if you’re looking to develop a voicebank or engine, especially in the west. While crowdfunds are great, we’ve only had a few over here and ngl crowdfunding and engine definitely isn’t going to work out rn considering Maghni AI’s state and the recent failure of Mikoto Studio’s. People over here might be more wary than ever about contributing to crowdfunding if it’s a whole engine. Just voicebanks might be okay.

Not sure if this is me regurgitating anything I said before but that’s where we’re at rn.

fwiw Eclipsed didn't have any particularly well-known people involved, they just pitched a voicebank people had been asking for and were reasonably qualified to do it

>>28134
Circus helped promote it

voimelo.png - 106.14 KB (855x199)

>>26903
TIL this happened last year

>>28639
But why

>>27147
That's if it was Synth5 but it's SynthV. V as in Vocals not the number 5.

>>21967
I doubt we have users like this at all but it'd be nice if some batshit insane codefag started writing a vocal synth engine with multilang support like Maghni now that the project's in flames

>>30362
the western synth curse will strike again in one way or another

>>28639
That is a terrible idea but i guess it makes sense for a mobile app. Mobile apps are aids when it comes to microtransactions and related stuff.

For anyone interested it seems the source code for maghni will be released

>>30555
Was it confirmed?

>>30561
They're not going to release everything but they put out a couple components
https://github.com/crescendia-dev/maghni-flow
https://github.com/vocatart/mina