AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ11

VerifiedImplement text analysis solutions

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 the call transcripts and detect issues while calls are still in progress. The call audio arrives as a continuous stream from the telephony system.

You need the call transcripts to appear within only a few seconds of the audio stream.

What should you do?

Explanation

Real-time speech to text processes a continuous audio stream and returns partial and final transcription results within seconds, which is required for supervisors to view transcripts while calls are still in progress. Batch transcription is designed for asynchronous processing of already-recorded audio files and has much higher latency, making it unsuitable for live monitoring. Text to speech with a custom neural voice generates audio from text rather than transcribing it, and speech translation converts transcribed speech into another language rather than providing the low-latency transcription itself.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!