0

Lets say I want to have some English text spoken in an Italian accent.

Many of the engine demos I have tried on their respected sites will have the Italian language available, but when you try to get it to pronounce a few sentences in English, they often become highly unintelligible because they are operating by a different phoneme.

There are phoneme tags in SSML, and I know one site that allows you to actually demo with SSML. I try putting in this common and generic Italian conversation into their Italian voice:

Mama mia! Princess Peach and my friends have been kidnapped?
Chase Bowser, so we can eat some spaghetti!

And it is fairly unintelligible. Utilizing SSML or something else; Can I keep the accent, but correct the speech phoneme enough to make it intelligible?

Matt Mills
  • 8,692
  • 6
  • 40
  • 64
Anon
  • 2,267
  • 3
  • 34
  • 51

1 Answers1

1

You can hire a voice-talent with Italian accent and make a new TTS model where such option is available. Even with a several hours of speech you can get a decent model.

The second option is speech morphing, but it requires some efforts as well as knowledge in the domain.

Alexander Solovets
  • 2,447
  • 15
  • 22