• If you do not recieve your confirmation email within a few hours, please email haloutau@gmail.com with your username for manual validation. Your account should be activated within 24 hours.
    You may also reach out via any other listed contact on Admin Halo's about page: https://utaforum.net/members/halo.194/#about

UtaForum.net

G
GreenPear03
Was the soft voicebank also rendered with RVC like Alex's standard VCV?
SaKe
SaKe
You can also open the oto in Notepad, go to replace and do something like
=
to
=S_
And set S_ as the prefix.
turboking
turboking
yes! All of his voicebanks were done using the RVC to UTAU method.
G
GreenPear03
Nice! I see many of Near's voicebanks made using RVC, and CABLE stands out to me the most for being a completely artifical voice, yet sounding extremely clear and natural.
turboking
turboking
yeah it's kind of crazy. I remember getting the demo back for the soft RVC model and having to do a double take because it sounded way too clear and natural. [positive] I could have sworn I actually sung that but I didn't LOL It sounded almost exactly like the raw dataset I gave them.
G
GreenPear03
Especially for RVC. How much training data did you give the trainer? I'm wondering if its like Diffsinger where it needs around an hour or more of data to sound natural.
turboking
turboking
It was only around 7 minutes of data which was the really crazy part.
Natsucchii
Natsucchii
nice
G
GreenPear03
I think the RVC models that Sunnywolves are planning on making with my UTAU voicebanks (multipitch VCV) will turn out well if your voicebank was made with only 7 minutes of training data.
turboking
turboking
G
GreenPear03
I just listened to the model, and it sounds just like a SynthV AI voicebank! Do you plan on releasing your RVC models with your UTAU voicebanks?
Top Bottom