nneko
Reaction score
36

Joined
Last seen

Profile posts Latest activity Postings Media About


  • Still a little choppy, but the timing is better than my first attempt. I was hoping that adding fake V C would make it sound smoother, but it's probably better to avoid the extra work.
    I don't plan on doing anything more with this voice bank.
    Trying to replicate speech/rapping parts of a Vocaloid song makes my head hurt.
    I converted an UTAU CV voice bank to DeepVocal just for fun (plus I needed some practice using the toolbox). It sounded better than I thought it would. The timing is slightly off, but I think it's possible to have a decent DV voice bank that only uses CV samples.
    JamesOvO
    JamesOvO
    how did you do it?
    I tried that but it keeps saying there is no V X and needs ho have V X
    nneko
    nneko
    @feelingiconiic
    I don't have an example right now. I want to try to improve it first.

    @JamesOvO
    I made fake V X using the end of the CV sample.

    I think there's an easier way to do this, so I'm going to start over from the beginning.
    Kiyoteru
    Kiyoteru
    It's possible to create and use incompletely configured DeepVocal voicebanks, and it's not going to cause anything like software crashes. The warnings are mainly reminders of what's missing to help you set up a complete voicebank that works smoothly. If you're using an incomplete voicebank, DeepVocal will try to do its best with the limited samples it has, so you shouldn't expect perfect results.
    Tried to get doppeltler to read .ogg. I did what the readme says, but it won't work for me.
  • Loading…
  • Loading…
  • Loading…
  • Loading…