Hi, our company has a strong desire for the low latency use case of the audio-to-audio endpoint for voice conversations. Highly anticipating the release thereof. Thank you @openAI-team for all your work on the subject. @logankilpatrick
Following - really need this too.
Same here. Also the desktop app, waiting to test invoice processing, capture, and ERP integration.
It seems they listened to my request, and today I got the app.
However, I’m a little bit disappointed: the charts and the way it handles data (even though I’m using 4-o model) seems from the previous experience.
Also, I’m not sure if the voice model is the latest one. I have to press a button to interrupt the conversation.
Other than that, I loved the screen capture feature: that’s something useful in my industry.
Now another question: will be a Windows app to be released??
How did you get the app? I am a pro subscriber, with api credits and… nothing yet…
When will API audio access be released? Can anyone from OpenAI confirm this?
My company is also very excited about the audio-audio feature. Is there any info about what the API will look like or how to become an alpha/beta tester?