Consider the following VoCo project from Adobe.

In it they show how they are able to take 20 mins of speech and create additional narration in the same voice very accurately.

Is there a neural net or something that is available in the language that can produce similar results.

  • 2
    $\begingroup$ As far as I'm aware, no network likes this exists in the language or the neural network repository at present, but that's not to say it's impossible to build! $\endgroup$
    – Carl Lange
    Aug 11 '19 at 8:17

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.