Comment on AI headphones translate multiple speakers at once, cloning their voices in 3D sound

captainastronaut@seattlelunarsociety.org ⁨3⁩ ⁨weeks⁩ ago

• SatansMaggotyCumFart@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  Why do you need someone’s permission to translate them?

  source

  • smiletolerantly@awful.systems ⁨3⁩ ⁨weeks⁩ ago

    To clone their voice

    source

    • Sandbar_Trekker@lemmy.today ⁨3⁩ ⁨weeks⁩ ago

      It’s not sending the audio to an unknown server. It’s all local. From the article:

      The system then translates the speech and maintains the expressive qualities and volume of each speaker’s voice while running on a device, such mobile devices with an Apple M2 chip like laptops and Apple Vision Pro. (The team avoided using cloud computing because of the privacy concerns with voice cloning.)

      source