AI-103 Certification Practice Question #58

Question

You are building a speech processing solution in Microsoft Foundry for a customer support platform.
The platform will transcribe live phone calls, so that supervisors at your company can view call transcripts and detect issues while the calls are in progress. The call audio will arrive as a continuous stream from the telephony system.
You need to ensure that the call transcripts appear within only a few seconds of the audio stream.
What should you do?

Accepted Answer

The platform must transcribe live phone calls from a continuous telephony stream with only a few seconds of latency. Real-time speech to text is the Azure Speech feature built for exactly this — it transcribes audio as it is recognized and emits low-latency intermediate results for live audio, which MS Learn lists as ideal for assisting customer-service representatives. Batch transcription (C) only processes completed recordings, text to speech (A) is the opposite direction, and speech translation (B) solves a different problem and adds latency. Suggested Answer and MS Learn agree clearly; 92%, reduced only for absence of community votes.

More AI-103 practice questions