I have a recording of a singing voice and would like to hear it with the voice of someone else.
There are many AI solutions out there but they seem to be either real time voice changing for gaming, text to speech, or pre-made synthesized voices, like Vocaloid.

I have seen videos of Arnold Schwarzenegger singing The Sound Of Music, very funny, very realistic, and expressive, so it is possible.

Is there a simple solution out there where you can load up one recording as a source and another recording as modulator and get a morphed wav file to download? Or some software that lets you do this type of thing without too much hassle?

I watched this video and it seems interesting. However, it seems you need a pre-made voice model?:

Any recommendations?

 

Here you go -> GitHub - voicepaw/so-vits-svc-fork: so-vits-svc fork with realtime support, improved interface and more features.

 

Thanks for pointing me in the right direction. It seems a bit complicated, I guess I´ll need to install Python and some other things.

 

You can also join the AI Hub discord server, lots of infos & vocals models there: https://discord.com/invite/9Aeep9sJrt