The “Advanced Voice Mode” will be a game changer for the AI-consumer interface I am developing when it becomes available to developers through the API. I searched this forum but cannot find any information on when it may be available. Des anyone have any insight on when it may be available through the API? Also, should we expect real time streaming both ways and the ability to interrupt like in the demos?
There is no planned API release.
there is no information about it.
I have noticed note that it will be available on end of fall , it is small point when using normal voice
OpenAI hinted at an API availability in their release post:
We plan to launch support for GPT-4o’s new audio and video capabilities to a small group of trusted partners in the API in the coming weeks.
That’s all we know so far.