Meta, the guardian firm of Fb and Instagram, introduced a speech-generation AI mannequin known as Voicebox on June 16.
The corporate mentioned Voicebox may generate speech from textual content and famous that the mannequin may match an audio fashion based mostly on a pattern simply two seconds lengthy.
Voicebox may 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 current recordings to take away background noise. Extra usually, it will probably create speech that’s modeled on various speech samples.
Voicebox could possibly be leveraged by varied customers
Meta mentioned that Voicebox and different related AI fashions may permit digital assistants and non-player characters in its metaverse to have lifelike voices. The software 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 mission. It didn’t say when the function could be publicly out there, however it shared a demo video.
Meta introduced a number of shopper AI instruments earlier in June, revealed particulars about its AI chips in Could, and mentioned inside AI purposes in an April investor name.
The publish Meta unveils speech era AI: Voicebox appeared first on CryptoSlate.
/cdn.vox-cdn.com/uploads/chorus_asset/file/25829977/STK051_TIKTOKBAN_B_CVirginia_C.jpg "The Biden White House says TikTok’s threat to go dark is a ‘stunt’")
