QuestionQ89
VerifiedImplement generative AI and agentic solutionsYou are developing a customer support web application called App1 in Microsoft Foundry that uses a GPT realtime model.
App1 must support:
- Live, low-latency voice conversations powered by Azure OpenAI
- Streaming audio input from users, along with playback of audio responses
You need to select a connection method that supports real-time audio streaming within the client application and achieves approximately 100 ms of latency.
Which connection method should you choose?
Community Discussion