Posts

Some info about Spanish voicebank's design

Image
As I've said before, some time ago after releasing Suu's first voicebank, I wanted to listen him singing in my native language: Spanish, and that's why he will have a voice library for this language soon. However, this is not only a matter of "I wanna listen the anime guy with my voice sing a song I can understand" . One of the things I like about UTAU is it has a rich and mixed culture, and I'm not only talking about content creators & fans, but also about voice library creators; voicebanks made by people from different countries around the globe and different social, ethnic, linguistical and minority groups, etc... There's also voice libraries made for foreign languages besides English and Japanese! And this is a beautiful consequence of UTAU itself being free software as in "free speech" , not only as in "free beer" , just like GNU's classic analogy.  Even a class worker guy from a third-world post-apocalyptic Latinoamerican ...

Spanish voicebank alpha prerelease

I've decided to release an alpha version of Suu's Spanish voicebank!! This is not a final version and it might be unstable or have some issues. Some of my followers from X were interested on testing it, so why not?   Some relevant info: This version has only two pitchsets: E3 and G3. The rest of them (C4 and F4) are still being configured; their oto.ini files aren't finished yet, so I preferred not to include them for now. I'll include these on a next release, maybe the final stable version... This means the optimal range of this version is roughly G2~C4. I suggest testing it on songs with low registers. This voicebank is based on the nJokis recording method, so you'll have to select ES VCCV phonemizer when you're using it.  ES VCCV has been having some issues since OpenUtau's latest beta & alpha updates. Please use UtauV or another OpenUtau fork while this is solved. Please check the readme.txt file to see more info and details.  I'm open to suggest...

CVVC voicebank minor update

     Did you know I'm also working on a minor update of Suu's CVVC voicebank? This would be the 2.1.0 version. In case you didn't know, I follow the Semantic Versioning scheme for labeling and releasing updates of any voicebank. If you wish to understand what the hell am I doing here (because this is not the regular UTAU voicebank release scheme/standard most creators follow), read a little about it here ...      So... this update will include a new feature: 2 new pitchsets!!!  These will be E3 and F#3. At first, I intended to add E3 only, however, after a lot of tests, I noticed the transition of this pitch to G3 sounded weird, so I recorded F#3 some time after.      Before releasing v2.0 (latest version), I actually thought about recording a low register pitchset. I even did it!! I had recorded a D3 pitchset and configured it, but the result sounded awful and I ended up discarding it for the final release of this version. The issue was...

Spanish voicebank development

Image
       As many of you may know, I've been working on a Spanish voicebank for Suu. I'd like to talk more about it...       I began working on this voicebank since some months ago (maybe May, I think...). This is my first time developing a non-japanese voice library and, dude.. this is being such a journey; I tried a whole different phoneme recording system (nJokis VCCV) along with a long ass reclist, like... 150+ recording lines. And things become even more fun because this is a multipitch voicebank!! I've recorded 4 pitchsets (E3, G3, C4 and F4). So... approximately more than 150 recordings per each one. Let's not talk about the oto-ini... The development of this voicebank is taking longer than expected due to many factors (daily power outages, I wasn't alone at home most of the time so I wasn't able to record freely, I was busy at the family business... etc.), I'm trying my best though. I've set a release date, and it will be... JANUARY 3RD, 2027...