QuestionQ56

VerifiedImplement AI solutions by using Microsoft Foundry

You are building an application that captures a user’s voice and sends the recorded audio to a deployed multimodal model in Microsoft Foundry.

You need to send the user’s request to the model.

What should the request include?

Explanation

Multimodal models that support audio accept recorded audio as an audio input prompt, allowing the model to process the voice directly. A text transcript is only needed if the application first performs speech-to-text conversion.

Learn more

Community Discussion

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