Microsoft unveils MAI-Voice-1, a speech model that can generate a full minute of audio in under a second on a single GPU, and a text model called MAI-1-preview (Reed Albergotti/Semafor)

Reed Albergotti / Semafor:
Microsoft unveils MAI-Voice-1, a speech model that can generate a full minute of audio in under a second on a single GPU, and a text model called MAI-1-preview  —  On Thursday, Microsoft announced two powerful AI models it built that it says perform at the level of the world's top offerings …



from Techmeme https://ift.tt/bBjNhzL

Comments

Popular posts from this blog

Guilherme Rambo, who has published scoops about unreleased Apple products by examining beta software, says Apple locked his dev account with no stated reason (Buster Hein/Cult of Mac)

Zombie startups

Autonomation