Looks like their TTS component is separate from the model. I just tried 4o, and ... | Hacker News

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

		caseyy on May 13, 2024 \| parent \| context \| favorite \| on: GPT-4o Looks like their TTS component is separate from the model. I just tried 4o, and there is a list of voices to select from. If they really only allowed that one voice or burned it into the model, then that would probably have made the model faster, but I think it would have been a blunder.

famouswaffles on May 13, 2024 [–]

The new voice capabilities haven't rolled out yet.

caseyy on May 14, 2024 | [–]

Oh, very interesting. The 4o model does now have TTS with a voice option similar to the one in the video, although objectively less over the top.

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