Like Sora… what happened there?
hello @owencmoore, I’m a product leader at Yepic AI; we are building visually emotive avatars and already process visual audio cues - how do we become a trusted GTP4o Audio tester? [my email] if you wanted to reach out
Yes sadly it is true
But if you are a developper im sure there is an audio to audio model already released on hugging face to do the job good enough
nothing close to what we saw on May 13th
Any ETA yet? It’s been several months already
+1 on this! It has been 4 months now. Any ETA please?
would love to use the voice model in my game for realistic NPC interaction
https://platform.openai.com/docs/guides/text-to-speech
Are you looking for this? Or do you want your players to be able to talk in realtime? Then realtime api might be right. Which is pretty expensive though. So caching would be neccessary.
OpenAI就这尿性,想想当时Sora吹得多牛逼,呵呵