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 dindindin on Monday April 21, 2025 @06:19PM (#43757134)

Was this trained on Planet Money / NPR podcasts? The last audio (continuation of prompt) sounds eerily like Planet Money, I had to double check if my Spotify had accidentally started playing.

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by jelling on Monday April 21, 2025 @06:43PM (#43757307)

NPR voice is a thing.

It started with Ira Glass voice and now the default voice is someone that sounds like they're not certain they should be saying the very banal thing they are about to say, followed by a hand-shake protocol of nervous laughter.

[ Parent | on HN ]

Re:Show HN: Dia, an open-weights TTS model for generating re... by genewitch on Tuesday April 22, 2025 @02:20PM (#43764866)

Thank goodness for Scott Simon!

[ Parent | on HN ]