AI-103 Certification Practice Question #12

Question

You have an Azure Speech in Foundry Tools resource that hosts a custom speech to text model deployed to a custom endpoint. An agent uses the endpoint to perform real-time speech recognition.
You are approaching the expiration date of the custom speech to text model.
What is the expected behavior when the model expires?

Accepted Answer

The scenario is a custom speech-to-text model deployed to a custom endpoint doing real-time recognition. Microsoft's custom speech model lifecycle doc draws an exact distinction by transcription route: for a custom endpoint, when the model expires "requests fall back to the most recent base model for the same locale" (you still get results, just without domain customization), whereas only batch transcription fails with a 4xx error. That maps directly to option C and eliminates A. B and D are not supported by the docs — the expired model is no longer used for transcription, and it is not automatically deleted. The Suggested Answer agrees with the authoritative doc, so confidence is high.

More AI-103 practice questions