I would like to clone a voice as precisely as possible. Lately, impressive models have been released that only need about 10 s of voice input (cf. https://github.com/CorentinJ/Real-Time-Voice-Cloning), but I would like to go beyond that and clone a voice even more precisely (with subsequent text-to-speech using that voice). It doesn't matter if I have to provide minutes or hours of voice inputs.

  • $\begingroup$ No idea about the answer but be careful: in some jurisdictions you could be sued if you use somebody's voice without their permission and make the result public. $\endgroup$ – Erwan Sep 18 at 22:44
  • $\begingroup$ There's a nice summary of the present technology by Derrick Mwiti, which doesn't really go into implementations but which may provide a starting point. $\endgroup$ – Bardi Harborow Oct 10 at 12:54

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.