Show HN: Dia, an open-weights TTS model for generating realistic dialogue

Re:Show HN: Dia, an open-weights TTS model for generating re... by DoctorOW on Monday April 21, 2025 @04:54PM (#43756357)

A little overacted, it reminds me of the voice acting in those flash cartoons you'd see in the early days of YouTube. That's not to say it isn't good work, it still sounds remarkably human. Just silly humans :)

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by selimthegrim on Monday April 21, 2025 @07:03PM (#43757460)

Reminded me of the Fenslerfilm G.I. Joe sketch where the kids have something on the stove burning

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by wisemang on Monday April 21, 2025 @07:23PM (#43757575)

Stop all the downloading!

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by Cthulhu_ on Tuesday April 22, 2025 @05:00AM (#43760252)

"flash cartoons in the early days of Youtube" Wouldn't those be straight from Newgrounds?

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by DoctorOW on Wednesday April 23, 2025 @07:44PM (#43777892)

Thank you! I couldn't remember the name Newgrounds for some reason!!

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by 3by7 on Tuesday April 22, 2025 @06:36AM (#43760682)

Overacted and silly humans indeed: https://www.youtube.com/watch?v=gO8N3L_aERg

[ Parent | on HN ]