How do I make a defoko-like voicebank

[J4ck_Blu3]

So recently I had the idea of making a semi-low quality voicebank, or a robotic voicebank. Something similar to Defoko's voicebank, however I don't know how to go about this, and unfortunately for me there are no actual tutorials of how to achieve this. If anyone knows or has an idea pleas share!

 

[NordGeit]

Defoko was made with samples from another vocal synthesizer, AquesTalk, which if I recall correctly has the voice synthesized from the ground up without any samples to begin with.
So if you want authenticity, you will have to find a sample-less vocal synthesizer, or start researching the source-filter voice synthesis model to make your own.
...
it would be funny if you actually did
Reduce your vocal quality in a program such as Tenacity (or an older fork of Audacity without the suswarez) by reducing the project rate and re-rendering (make sure to hold on to the original files), then try introducing some noise
Playing around, I found the Expand and Compress distortion type in Tenacity
anyways I'm not an audio engineer but this should bring you closer
ok break a leg bye

 

[SneezyEevee]

Well, there’s a few ways you can take your own voice and make it sound super robotic. If you have a DAW you could see if you have plugins like EQ, fx, or filter. In the EQ, try hiking up the mid frequencies and cutting the high frequencies for a muffled sound on your audio recordings. Then layer on something like a fuzz filter or distortion to add some cronch. Then add a pitch corrector with the highest level of snap (I think that’s what it’s called) to make it even more robotic.

 

[Ibis]

If you have a voicebank in mind that you want to make more robotic, I heard you can use the W flag in UTAU (you don't have to add any numbers after it, just a capital W). I don't see it used very often, but it seemed to work pretty well when I tried it out.

There are a couple of other voicebanks like Defoko that have been recorded with aquestalk (such as Yukkuri Reimu) that have synthetic voices too!

 

[Thehyami]

See the end of video:

How to Make Synthetic Voicebank

Also there are 4 videos in total on that link.

 

[underscoredotpng]

If you want to make a low-quality voicebank, you can edit the samples in audacity and resample them to a lower rate :D