Azure-Samples / aisearch-openai-rag-audio

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
https://azure.microsoft.com/products/search
MIT License
211 stars 105 forks source link

Feature request: Transcription of conversation #7

Closed jakeatmsft closed 3 weeks ago

jakeatmsft commented 3 weeks ago

Is there anyway to add transcript to the demo?

chuwik commented 3 weeks ago

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:

If you want a transcript of the responses:

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.

jakeatmsft commented 2 days ago

This code has been implemented in my fork: https://github.com/jakeatmsft/promptflow_patterns/blob/main/voice_app/app/frontend/src/App.tsx