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.
Hello!
Is it possible to capture both the generated output and input in text as well? Or do I need to implement some additional external resource specifically for this?
My intention is to maintain the current voice functionality, but I also want to have a text record
Regards
Hello! Is it possible to capture both the generated output and input in text as well? Or do I need to implement some additional external resource specifically for this?
My intention is to maintain the current voice functionality, but I also want to have a text record Regards