Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
The most realistic and instructible speech-to-speech foundation model (hume.ai)
2 points by pyman 75 days ago | hide | past | favorite | 1 comment


I've just cloned my voice and talked to myself. It sounded like me! Proper surreal.

More info here: https://www.hume.ai/blog/introducing-evi-3




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: