Posts in Category: Sticky posts
Something completely different
Hello everyone! It’s been a bit.
I haven’t really worked on a lot of vocal synth stuff as of late (not even for Hanami’s 15th anniversary… Oops!) but I have not “quit” or anything like that; I’ve simply been doing some other things. Such as developing an Android app.
No, said app has nothing to do with vocal synth either. It’s actually for old, archaic Japanese dress up games (pre-Flash, pre-most Javascript) called KiSS dolls (if you don’t know what these are, you probably won’t care about this app. Sorry!). I basically wanted an app that could open these on my phone, but the available options are all 32-bit apps for older Android. This app also works on the latest Android as well, and was built with it in mind.
The app is called DroidKiSS and you can download the latest release from the GitHub repo. It’s still in beta stage, so bugs are to be expected. Don’t be afraid to open an issue if you encounter any; I’ll try to fix them as soon as possible.
I’m actually planning on working on a subdomain website about dress up games (more info on that later), where I’ll post more information on this project, as well as some other dress up game-related projects that I’m working on.
That is all. Sorry for no vocal synth news! Yes I’m still gonna make a Hanami multidict DiffSinger model, don’t worry! It’s in the works, I promise.
~Lotte V
Permission for commercial use is no longer necessary
Hello everyone,
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
Project AI❤dol Public English Dataset
Hello everyone, I have more exciting news!
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 AI❤dol section.
I hope you enjoy! And please read the readme on the GitHub before using, thank you in advance!
~ Lotte V
Hoshino Hanami ~AI❤dol~ for DiffSinger v1.0 is out!
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 AI❤dol (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 AI❤dol. 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
Hoshino Hanami -LoveSong- for Diffsinger Beta2 is out!
Hey everyone,
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.
~ Lotte V
Welcome!
Hello, dear visitor! This is my website where I post things related to whatever I create. This ranges from vocal synth works (Vocaloid, UTAU, DeepVocal, CeVIO, etc.), original music works (which can be created with either vocal synth or my own singing), visual arts (this website will mostly focus on original works based on my own characters and stories) and writing (which includes the web novel I’m currently working on).
This site is currently a little bit empty, but proper content is coming soon! Please stay tuned as I get everything ready. Thank you for your patience!
~Lotte V