Meta announced a new AI model called Voicebox yesterday, one it says is the most versatile yet for speech generation, but it’s not releasing it yet: The model is still only a research project, but Meta says can generate speech in six languages from samples as short as two seconds and could be used for “natural, authentic” translation in the future, among other things.

  • Clairvoidance
    link
    fedilink
    21 year ago

    I well enjoyed our talk together too! Though just beware i might definitely post cringe shit on topics you don’t care about

    • Maeve
      link
      fedilink
      21 year ago

      Oh well, we’ll see how it goes. Cheers!