Using Utau resampler on regular voice recordings?

[Aqua]

Hi everyone,

Apologies if this is a weird ask, but hypothetically, if I wanted to record myself speaking, and then run it through Utau's resampler to make it sound closer to my Utau's voice (with the robotic-feel), would this be possible to do? Or can resampler only handle short phonemes?

I only ask because I've toyed with the idea of making Youtube videos for a while now using my Utau as an avatar. It would be cool if I was able to actually fully keep up the facade of her voice too!

If this isn't an option, is there anything else I could possibly use for this outcome?

Many thanks for any help!

 

[GreenPear03]

This would be possible to do! In fact, the song "They" by Crusher-P, was created using voice recordings put through UTAU's resampler.

 

[Aqua]

This would be possible to do! In fact, the song "They" by Crusher-P, was created using voice recordings put through UTAU's resampler.

Oh that's wonderful to know! I'm listening to that song now and it's everything I want the outcome to be. Is there any tutorial on how to do this? I'm presuming I'd just record the voice sample but then I'm not sure where I'd go from there?

 

[SunnyWolves]

you should just be able to record it as a sample and play it as a note in utau. No need to oto or anything.

 

[Aqua]

you should just be able to record it as a sample and play it as a note in utau. No need to oto or anything.

I just tried this but it seems I can only make the note so long before it cuts off. I'm using Utau-synth if that's any help. I do have access to a PC with regular Utau installed though!

 

[GreenPear03]

Maybe you should cut off the beginnings and ends of the phrases or words you say, and have the consonant/fixed region be where the last vowel in the word or phrase is, and have the preutterance be after the last consonant in the word, or the second to the last consonant in the word or phrase, depending on if the phrase or word ends in a consonant.