Hey there,
I’m migrating my product from realtime to live model and one thing I’m really missing is the ability to know when a turn from the voice model is over.
More specifically, I’m having a very hard time understanding how could I trigger this chain:
- voice turn
- tool call
- voice turn
without too much latency.
Would love to know how others handle that and if end of response event is in the plans for gpt live?
Best,
Anat