Hi, I need help training artificial intelligence or some method I don't know about to compose with my voice, such as with Synthesizer V from Dreamtonics. I know it has its “Vocoflex,” but it doesn't have a trial period, nor is it available on the sister site... So I'm wondering if anyone knows of a way to create a sound bank with my voice, so I can try out some crazy things that would take me a loooong time in real life, since my throat gets pretty tired after an hour. I do rap screams, to give you an idea... I've been using Suno to create songs and I really like it. It's key to use good prompts. But I can't find any way to put my voice in there :c


Thanks in advance.

 

You need an SVC or Singing Voice Converter tool - like this one: https://applio.org/
Basically you can use it to train a vocal model from your voice and then you could potentially take those suno outputs and make them sound like you but YMMV it depends on the quality of the input vocal and the quality of the training data.
You could also use something like https://acestudio.ai/ which is definitely more of the Vocaloid type of deal, but its a SaaS product so its paid with no chance of it ever being on sister site.

 

didnt know about SVC... its like a format? which not every app can read? or how it works?
yea acestudio takes my attention but cant pay that x_x

 

I was amazed at this project, seed-vc:
https://github.com/Plachtaa/seed-vc

It doesn't need to train your own models to use, just feed an original voice sample you want to replace and a reference sample you want to clone.
You can save a converted audio as a wav file.

 

IK Multimedia's ReSing may be what you are after. Just came out today @ https://www.ikmultimedia.com/products/resing/

 

wow this one looks interesting about that RVC thing... gonna check that!