Meta Platforms unveiled on Friday an artificial intelligence-powered speech generator called Voicebox, "a state of the art AI model that can perform speech generation tasks, like editing, sampling and stylizing, that it wasn't specifically trained to do through in-context learning."
Meta said Voicebox can read written text in multiple voices and styles, as well as fix background noise in audio clips. The feature currently supports English, French, German, Spanish, Polish and Portuguese and "can produce a reading of the text in any of those languages, even when the sample speech and the text are in different languages."
"We think this is probably the most versatile speech generative model out there. This is still a research project but I think we are going to build a lot of interesting things with tools like this," Meta CEO Mark Zuckerberg stated.
