forbiddenvoid 5 days ago

Lots of improvements here (hopefully), but still no image generation updates, which is what I'm most eager for right now.

2
taikahessu 5 days ago

Or text to speech generation ... but I guess that is coming.

dharmab 5 days ago

Yeah, I tried the 4o models and they severely mispronounced common words and read numbers incorrectly (eg reading 16000 as 1600)

Tinkeringz 5 days ago

They just realised a new image generation a couple of weeks ago, why are you eager for another one so soon?

nanook 5 days ago

Are the image generation improvements available via API? Don't think so