Easily 10 times better than recent OpenAI voice model. I don't like robotic voic... | Hacker News

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

		new_user_final 3 months ago \| parent \| context \| favorite \| on: Show HN: Dia, an open-weights TTS model for genera... Easily 10 times better than recent OpenAI voice model. I don't like robotic voices. Example voices seems like over loud, over excitement like Andrew Tate, Speed or advertisement. It's lacking calm, normal conversation or normal podcast like interaction.

toebee 3 months ago [–]

Thank you! You can add audio prompts of calm voices to make them a bit smoother. https://huggingface.co/spaces/nari-labs/Dia-1.6B you can try it here!

Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact