Kokoro is fine for TTS, but it lacks emotion. But for a model of this size, that... | Hacker News

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

		ekianjo 21 days ago \| parent \| context \| favorite \| on: Abogen – Generate audiobooks from EPUBs, PDFs and ... Kokoro is fine for TTS, but it lacks emotion. But for a model of this size, that is kind of given.

robin_reala 21 days ago | [–]

Ironic given the name: kokoro is Japanese for heart or sentiment.

SirHumphrey 21 days ago | [–]

I played with ebook generation a bunch and find that (at least for English text) around 1B is needed to get something usable emotionally (Chatterbox is 0.5B, Orpheus is 3B).

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