Meta, the mum or dad firm of Fb and Instagram, introduced a speech-generation AI mannequin referred to as Voicebox on June 16.
The corporate mentioned Voicebox might generate speech from textual content and famous that the mannequin might match an audio model based mostly on a pattern simply two seconds lengthy.
Voicebox can even convert a textual content pattern to a different language and, given a separate speech pattern, learn the translated textual content within the speaker’s unique voice. This functionality helps six languages: English, French, German, Spanish, Polish, and Portuguese.
The AI mannequin can moreover edit present recordings to take away background noise. Extra usually, it could actually create speech that’s modeled on numerous speech samples.
Voicebox could possibly be leveraged by numerous customers
Meta mentioned that Voicebox and different related AI fashions might permit digital assistants and non-player characters in its metaverse to have practical voices. The instrument may be of use to content material creators and to customers with accessibility wants, it mentioned.
Meta mentioned that Voicebox is at the moment a analysis undertaking. It didn’t say when the characteristic may be publicly out there, but it surely shared a demo video.
Meta introduced a number of consumer AI tools earlier in June, revealed particulars about its AI chips in Could, and mentioned internal AI applications in an April investor name.
The put up Meta unveils speech generation AI: Voicebox appeared first on CryptoSlate.
Discussion about this post