I suspect podcasts, as you have a huge amount of transcribed data with good dict... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

xdfgh1112 on April 22, 2025 | parent | context | favorite | on: Show HN: Dia, an open-weights TTS model for genera...

I suspect podcasts, as you have a huge amount of transcribed data with good diction and mic quality. The voices sound like podcast voices to me.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact