AI-103 Practice Question 39: Custom Voice Brand

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 4 · question 9 of 10

Implement text analysis solutionseasy

A retailer wants its voice assistant to speak with a distinctive, recognizable brand voice recorded by an actor the company has contracted, rather than with one of the standard voices its competitors also use. The team asks what the work actually involves before committing.

Which description is correct?

Show answer and explanation

Answer:

C. Request access to custom voice, record and submit the voice talent's consent statement, train a voice model on the recorded utterances, and deploy it to an endpoint

Custom voice is the text to speech feature for building "a one-of-a-kind, customized, synthetic voice" from human speech samples, and the documented sequence is exactly this. Two gates catch teams out: access is limited based on eligibility and usage criteria and must be requested through an intake form, and before you can fine-tune a professional voice you must submit a recording of the voice talent's consent statement. Microsoft recommends at least 300 utterances for training. Once deployed, you still shape delivery (pitch, rate, intonation, pronunciation correction, and style switching) with SSML.

- A is wrong because SSML prosody adjusts an existing voice's delivery. It cannot change the timbre and identity of the speaker, which is the whole point of a brand voice. - B is wrong because fine-tuning a language model changes the words chosen, not the voice that reads them. The output would still be synthesized in the standard voice. - D is wrong because phrase lists bias *speech to text* recognition toward expected words. They play no part in speech synthesis.

Reference: Custom voice overview

Practice Test 4 ›

Study guides for AI-103

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.

AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.

How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.

AI-901 exam guide: Azure AI Fundamentals after AI-900AI-901 replaced AI-900: learn what changed, how much Python and Microsoft Foundry you need, exam costs in India, and how to prepare.

Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.

Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.

AI-103 Certification Guide: What Changed From AI-102The AI-103 certification replaced AI-102 in 2026. Exam format, cost, the five skill domains, what changed and how to prepare, with free practice questions.

What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.

Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.