This has been a very difficult decision to make, but I wanted to get it out there in order to prevent confusion as to where I suddenly went.

TL;DR: I’m going on an indefinite hiatus from vocal synth. Yes, I know this contradicts what I said in my previous post and I sincerely apologize for that. More details under the cut.

As you can read from the title, I’ve decided to go on an indefinite hiatus from vocal synth. Calling it a “retirement” sounds too drastic — since there’s always a slim chance that I might return one day — but I wouldn’t count on any sort of guaranteed comeback. Just keep in mind that the chance of me never returning does, in fact, exist, and just in case that happens: please don’t worry about me, I’m probably fine.

As I’ve said, this was a very difficult decision to make. Vocal synth has been a part of my life for 15 years now, and to be honest, until surprisingly recently I expected to easily add 15 more to that, but then one day I just realized this wasn’t in the cards. It honestly feels like a sort of breakup — leaving a community (even if possibly temporarily) after 15 years isn’t exactly easy. When I decided this, it honestly felt like a part of me was taken away; as if a marriage had fallen apart. I know the comparison sounds silly, but it genuinely felt that way, and still does.

Why I’m stepping away

The exact circumstances as to why I’m going on indefinite hiatus isn’t something I’d like to discuss in public, as they’re very personal and not really of anyone’s business. But to keep it general, I’ve realized that I simply don’t feel like I belong anymore. I lost my motivation in specifically UTAU quite a while ago, since it no longer meets my standards of quality (due to this, please don’t expect any UTAU voicebanks coming from me anymore; I’m essentially done with it. I’m very sorry about that). I then moved on to DiffSinger, which motivated me to keep going for a while, but I’ve recently lost motivation for that as well for personal reasons (please don’t ask for details).

To be honest, the “not quite belonging” part is something I felt very quickly into my vocal synth journey. I’ve always had somewhat different creative visions from the rest of the community, as well as some other points where I just differed from the rest. But what kept me going was the positive interactions with the community despite all this. Differences aren’t necessarily a bad thing, but when it gets to a point where the differences are in conflict with each other, it’ll just no longer work out.

Another reason is that I want to make music again for a general audience. I no longer want to make “music for vocal synth fans”. The truth is that using vocal synth will put you in a sort of niche, and people outside that niche won’t understand the appeal. And you can’t just make them understand; they have to do that by themselves, and most of them never will. Some people are OK with this, but it’s something I’ve always struggled with since I’ve always been too embarrassed to show my vocal synth projects to the people closest to me, and that has always hurt me. It has actually somewhat prevented me from forming friendships that I so desperately need, because nobody really understands your arguably biggest hobby at that moment. (Yes, I know I said I wouldn’t get too personal, but this is something I felt important to share.)

And then, when your “niche” happens to be a community you feel estranged from… Why bother at that point? Why not go into the world and make friends elsewhere instead?

The future of my characters

The short answer: I don’t exactly know yet.

I’ve currently put aside all my WIP voicebank projects, including the planned multidict DiffSinger updates. Please don’t expect these updates any time soon, if ever. (And as I’ve said before, I no longer use UTAU.)

A few things I will say, though:

• If I do decide to keep my characters around in some form, I’m going to rename Hanami. “Hoshino Hanami” as a name has been a burden on me ever since my first day of doing vocal synth. It’s unnecessarily Japanese-sounding and “weeb-y” and that’s just not something I’d do anymore right now. She’s not Japanese and has no attachment to Japanese culture. I did mitigate the issue somewhat by fixing the Japanese spelling of her name, but the truth is that I was never happy with it. The only reason I kept it around was due to the fact that people knew her under that name, and I didn’t want to confuse anyone (and this reason is less relevant now due to me stepping away). My other characters will keep their names, since I never had issues with those. I will reveal Hanami’s new name in a different post, if I decide to go through with this plan.
• “Hanami” would also be getting a makeover. Right now I’m an adult woman in my 30s (as opposed to the 19 year old girl I was back in 2011) and her current look with the pigtails is starting to look too juvenile. She will look and dress like an adult woman, just like myself.
• I might write a story featuring my characters. Who knows, if I can think of any interesting lore.
• I might train RVC/other types of voice conversion models of my characters (and if not my characters, just my natural voice with an avatar). I still like the idea of “open-sourcing my voice” to music producers and other interested parties — I just no longer believe that vocal synth is “the solution”. Like it or not, the current AI trend also makes this appealing to the general audiences that I mentioned before. I’m still staunchly opposed to unethical AI and always will be, but if I consent to it, nobody is getting hurt. DiffSinger is AI too, anyway.
• “Project AIdol” is essentially dead. I was going to make a “DiffSinger girl group” featuring “Hanami”, LEONA and QUiNN, but I no longer have a desire to do so. I’m very sorry to anyone who liked this idea; I never spoke too much about it in public since it was still in its planning stages, but don’t expect much from it anymore for the time being.
• That being said, the dataset stays, but will probably get a different name. As I’ve said, I still like the idea of “open-sourcing my voice”. I might also allow custom model training featuring my voice (which was practically banned before), including for things like RVC (but also DiffSinger!). NOTE: RVC-ing over the corpus for training DiffSinger banks will remain banned. That’s what multispeaker is for.
• The alternative to all this is that I’ll redesign my mascot Vee (who I was actually planning on retiring, since I currently find her boring). She’ll no longer be a 1:1 copy of me “but with cat ears”. I want her to look “cooler”, more interesting. We’ll see.
• The third option: I could also keep both my characters as well as Vee around in some form, together, at the same time. Once again, I’m not yet sure!

The future of the DiffSinger wiki

Just in case anyone is unaware, I created a DiffSinger wiki on Miraheze a while back. Due to my current disinterest in vocal synth (and my admittedly poor management of the place), I plan to transfer ownership to someone I trust, preferably with wiki management experience. Who that is, I don’t know yet, but I hope to know soon. If I can’t find anyone, I’m afraid I’d have to close it (which I don’t quite want to do), but if that happens, feel free to start a new one from scratch without my involvement.

Moderating the DiffSinger Discord server

As some of you may know, I’m a moderator in the DiffSinger Discord server. While I’m not the only mod, I’m the only one who’s frequently active. Obviously the first thing that might come into your head is that I should step away, but I can’t — the owner of the server, OxygenDioxide, has been MIA for a while now, and he’s the only person who can grant mod status to people. So without me, I’m afraid the server would severely decline in quality.

I’m still pondering a few things:

• I could ping Oxygen to tell him I’d like to rescind my mod status and to instate some new ones, but I’m not sure if he’ll see the message.
• I could ask the DiffSinger community to start a new server with an active admin who’s online often, with more moderators who live in various time zones. I would obviously not be involved with this server in any form.
• I could just leave and let the server “rot”. This is an absolute last resort that I do not want to do; I’m not that evil.
• Another (terrible) alternative is that I keep permanently lurking “in the shadows” as a mod, but I also ideally don’t want to do that, since I’m no longer a real part of the community.

I’d like feedback on this, because I really don’t know the best course of action. This isn’t like the wiki where I can do whatever I want.

This website (and my current voicebanks)

This website won’t be going anywhere, however it will get a makeover sometime in the future. At the very least, the voicebank links will be removed, as well as the current character profiles (this does not mean the characters are “dead”; if I ever bring back their profiles, they’ll be at a different location). What I’ll do with the voicebank uploads themselves, I don’t yet know — I always said that I’d keep my voicebanks online even if I were to ever lose interest in vocal synth, but to be honest, I’m not quite sure anymore right now (this doesn’t mean I’ll definitely delete them, only that I haven’t decided yet). The direct links will go though, since they no longer reflect my current interests.

My plans for the future

As I’ve stated above, I’m not going to stop making music. Instead, I’ll go back to making music featuring my actual singing voice — and if I keep my characters around, I might even sing “character songs” for them. It won’t be vocal synth, but it’s still something! And the RVC model will come, no matter what its “face” will be.

I’m also going back to an old hobby of mine: dress up games. I used to make my own when I was younger, and I recently (even long before the hiatus) rediscovered how much fun they can be. The big difference is that I’ll use modern technology now (HTML5) instead of the crusty old (and obscure!) tech I used before. (And yes, the dress up game site/subdomain/whatever is still in the cards! Very much so. I’m excited to get started!)

I’ll also keep on drawing, coding, writing, and do all my other hobbies. Who knows, maybe we’ll bump into each other in different places where we least expect it.

Don’t get me wrong, this community has brought me some unforgettable memories. I was even part of an UTAU album collab once, and I met my now ex-boyfriend there. That’s certainly not nothing! But, I’ve also accepted that this is all in the past. I’m a different person now than I was back then, and I want to move on.

—-

That’s all I have to say for the time being. Perhaps I didn’t even need to write such a sentimental post, but I felt like doing so for the sake of transparency. I don’t like the idea of just “leaving” without a trace and having everyone wonder where I went.

Either way, I hope you understand and respect my decision. See you… somewhere, someplace, sometime.

~ Lotte V

I’m writing to inform you all that I’ve decided that asking for permission for commercial use is no longer necessary for any of my voicebanks. I keep getting emails about this and honestly, it just gets a bit tiring to reply with “yes” every single time! Because truth be told, I don’t care at all about commercial use and haven’t for a long time now. (Don’t misunderstand; I’m not mad at people for asking! Because it’s understandable. I’m merely clarifying my current stance.)

I’m aware that my UTAU voicebanks still have “permission required” in their readmes and whatnot, same with the UTAU wikis. But truth be told I’ve mostly retired from UTAU development (I’ve shifted focus to DiffSinger) so I can’t be bothered to update any of that anymore. My DiffSinger voicebanks have explicitly stated that permission isn’t necessary from the very beginning.

So in short, I’d kindly ask to not send me any emails regarding this anymore because I don’t care and the answer is always “yes”.

That is all for now! I actually plan to eventually update all my character pages on here with more recent information, but I’ll do that once I have more time. More info about this in the next post.

~ Lotte V

I have decided to publish a selection of my own SVS dataset for parallel training. You can use this data to help create your own DiffSinger model (or any other suitable SVS software). There has been a severe lack of easily available English female data, which motivated me to release the corpus.

I’m planning to make a proper dataset page someday, as part of the Project AIdol section.

I hope you enjoy! And please read the readme on the GitHub before using, thank you in advance!

Download on GitHub

~ Lotte V

Hello all!

I’m happy to announce that Hanami’s DiffSinger voicebank has finally gotten a full official release! As you can see, I ended up changing the name of the voicebank in order to match Project AIdol (see logo at the top of the post).

There’s some general information about the voicebank in the video description; I’m not gonna add all of that here, since that would make the post way too long. But what I will say is that she supports many different languages, has 3 different vocal modes, auto-pitch, and a custom vocoder.

I’m planning to create a dedicated DiffSinger section to the website, as well as some general information about Project AIdol. It’s probably gonna take a bit before I can do that though, but please be patient! It will happen, I promise.

You can download the voicebank here.

I hope you enjoy using her!

~ Lotte V

A new beta for Hanami’s DiffSinger model is out. Hopefully LEONA will follow soon.

This beta was trained with reflow and has 3 vocal modes instead of just 1. And again, still in beta, so apologies if there are still weird quirks around! Please let me know if you encounter anything strange.

Download link on GitHub

~ Lotte V

They’re very unfinished but enjoy them regardless. The only ones that are missing are either a) experimental, or b) not something that’d be allowed on GitHub.

My other UTAUs will come at a later date.

Have fun. I’m going to bed now

~ Lotte V

Yes, you’ve read that right! Hanami and LEONA’s DiffSinger models are now in beta. I won’t be adding them to their respective character pages yet due to their beta status, but I still wanted to have the links here on my site. So for now I’m posting them as a blog update.

Hanami download link

LEONA download link

I recommend you read the release notes before downloading; they contain some pretty important information.

Have fun!!!

~ Lotte V

Hopefully this helps some people with their projects, and hopefully the results will be satisfactory enough.

Speaking of Diffsinger… Be on the lookout for that the coming time.

~ Lotte V

The voicebank got released a few days ago, but I forgot to make a post… Oops!

Finally, she’s here! It took me a long time, but I finally did it. This release was originally for QUiNN’s 10th anniversary, but I drew a complete blank when it came to inspiration for quite some time when it came to her design. Even though the voicebank had been finished for some time already… Oh well. I hope you like it regardless!

Her page on this site has also been updated, although as of writing this post I still need to finish the final touches. Those will come with time.

Again, I hope you like her!

~Lotte V

I haven’t mentioned this yet on the blog, but sometime last year (2022), my Blue Yeti microphone that I’ve had since 2015 unfortunately broke down. Do not fret, however! Not long after this happened, I bought a new microphone, a Rode NT-USB to be precise. This means that I can still continue recording, and in my opinion, this microphone offers higher quality audio, which means that my future voicebanks will sound even better than they did before.

However, there’s an obvious downside to all this: I have to rerecord everything. Again.

What probably bothers me the most about this, is that several of my UTAU voicebanks had either been updated not too long before my microphone broke, or I had been working on updates that were to be released in the near future. Unfortunately, in order to have a matching quality among all voicebanks, combined with my personal perfectionism, I do feel obligated to rerecord everything again. I am currently in the process of doing so.

This also means that Joëll, who had literally just been updated before my microphone broke, will have to get updated again, relatively soon after his last update. No, I don’t like it either, but again, I feel obligated to do so. Especially since I had already been planning to record an alternate English voicebank for him, recorded with a different method (more information on this in future posts), even before my Yeti broke. But I sadly can’t do anything anymore with the in-progress Yeti recordings I did have… So I have no other option. A possibly positive aspect of this, though, is that I’m currently looking into making his MidNight (soft) voice color/append tri-pitch, so that its range will match the other two colors/appends. I’m trying to make his new English bank tri-pitch as well; his current one is a bit lacking in range.

I’m also currently working on updating Hanami, whose update… was also relatively soon after the last one, but at the very least I never actually got to finish my updates for Korean and Chinese, so those will be coming, as well. And same as with Joëll above, a new English bank will come as well, same with Spanish. I’m trying to make all these banks tri-pitch.

QUiNN‘s new Japanese bank has actually been finished for a long time now; unfortunately, I’ve been lacking inspiration for her concept art, which I find rather unfortunate. I hope I’ll get the inspiration to resolve this problem.

Annushka‘s “Japanese Plus” (aka Japanese with some extra consonant sounds) is already fully recorded, but not yet fully configured. I also still need to draw her new concept art. However, I hope to release QUiNN’s update first.

LEONA had only gotten a newly-recorded extra pitch for her Core voice, so for her I’m working on rerecording her whole bank rather than a simple “patch”. I also plan on giving her a new English bank.

Regarding DeepVocal

I have some news considering DeepVocal that might disappoint some of you: While I will not take Cecilia’s existing voicebanks down, development on her has unfortunately been stopped. This also means that her planned male counterpart, Dorian Calmato, will not be released. Cecilia’s planned English voicebank, as well as the Soft, Power, and Cute Japanese voicebanks, have also been scrapped. I’m very sorry about this!

Instead, I’m considering uploading her source files (audio files/DVCFG files/etc.) of each existing voicebank to a git repository, making her effectively open source in the process, akin to my UTAU voicebanks. The reason I’m considering this is because I’m aware that her currently released voicebanks contain some instances of sloppy configuration on my part due to a lack of proper knowledge at the time, but I also can’t be bothered to fix them due to my diminished interest in DeepVocal development. So, for those who are interested, I am willing to let users themselves reconfigure her so that she will sound better, if they so desire.

Believe me, this was not a light decision to make. Cecilia as a character concept essentially represents a sort of “what if?”-situation, had I gotten into UTAU now instead of back in 2011. The existence of DeepVocal, at the time, seemed like an opportunity to me to essentially start “from scratch” with a character I’d actually be “100% behind”. However, when Hanami’s 10th anniversary arrived, I saw the opportunity to give some of the concepts that had been wandering in my mind to her as well as a sort of “character reboot”, which meant that Cecilia, unfortunately, started serving less of a purpose. This, combined with the fact that I admittedly find DeepVocal development to be an excruciatingly tedious process, and the fact that I became a dev for the wonderful software OpenUtau, has caused me to make the decisions I did. And again, I am not taking her voicebanks down – I am more than OK with people still downloading and using her! All I’m doing is step away from her development. I am setting her free.

I hope you guys understand this decision, even if you don’t entirely agree with it. I simply have a desire to concentrate full-time on (Open)UTAU again, just like how I started. It simply is my home.

So! This is the current overview of my update plans. There are a few more things I’d like to say about these updates, including something else that I have been considering, but I’ll save that for a future post.

That’s all for now. Hope to see you around!

~Lotte V