aisearch-openai-rag-audio
aisearch-openai-rag-audio copied to clipboard
Feature request: Transcription of conversation
Is there anyway to add transcript to the demo?
It's not currently displayed in the app, but you have the hooks ready to plug it in.
If you want a transcript of the user input audio:
useRealTimetakes aenableInputAudioTranscriptionparam, passtrueuseRealTimetakes aonReceivedInputAudioTranscriptionCompletedparam, pass a function that decides what to do with the message.
If you want a transcript of the responses:
useRealTimetakes aonReceivedResponseDoneparam, pass a function that decides what to do with the message. Checkout ResponseDone intypes.tsto see what it looks like.
I recommend you hack these together in App.tsx with simple console.log to start, then go from there.
We have plans to surface these plus the grounding data in a 'transcript' view, but no ETA.
This code has been implemented in my fork: https://github.com/jakeatmsft/promptflow_patterns/blob/main/voice_app/app/frontend/src/App.tsx
Thanks @jakeatmsft for sharing! I'm re-opening this issue as it's a common request. @chuwik says that we also want a way to link the transcript to the grounding files ideally, for a full solution.
#44 PR in review adding this functionality