Hi ,
Does anyone has any idea on when will the real time Audio capabilities with better latency wil be available to api ?
I have heard that Open ai has already enabled this to Chatgpt plus users .
Currently because of Latency only Groq has dominated the market .
And that too with Llama3 which is not at all useful for me atleast.
There hasn’t been any sort of indication that this feature will be available for the API.
Assuming that OP is talking about the Advanced Voice Mode which does have much lower latency, 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.
Whether or not they plan to extend this to regular API customers is up to anyone’s guess though.