Hi Devs,
I was trying real time transcription, but as it turns out it is not as realtime as you might think it to be. Let me please clarify.
They say in docs: " For gpt-4o-transcribe
and gpt-4o-mini-transcribe
the delta
event will contain incremental transcripts as they are streamed out from the model." But I do not receive any delta updates when I speak long sentences. But I receive all the delta updates as soon as I finish speaking a big say 50 word line, while I wanted each word.
Github Sample: https://github.com/Sahil-Bagdi/PythonRealTimeMicTranscription
This Sample will demonstrate you what I am talking about, Just keep the API key in the ENV
Thanks