Re:OpenAI Audio Models
by minimaxir on Thursday March 20, 2025 @02:43PM
(#43427263)
Passing the generated audio back to GPT-4o to ask for the structured annotations would be a fun test case.
[ Parent
| on HN ]
Re:OpenAI Audio Models
by jeffharris on Thursday March 20, 2025 @07:37PM
(#43430288)
this is a good solve. we don't support word time stamps natively yet, but are working on teaching GPT-4o that skill