AI-102 Plan and manage an Azure AI solution Practice Question
You are planning to deploy a custom neural voice (CNV) model using Azure AI Speech. You need to ensure that the deployment meets Microsoft's responsible AI requirements. Which two actions should you take? (Choose two.)
⚠ Common exam trap
The trap here is assuming that custom neural voice can be deployed without Microsoft approval, when in fact it requires a gated access application and consent.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Submit an application to Microsoft for access to custom neural voice and wait for approval.
To deploy a custom neural voice model responsibly, you must obtain explicit consent from the voice talent and submit an application to Microsoft for access. These are mandatory steps in the gated access process. Using standard voices or training without consent does not meet the requirements. Deploying to a public endpoint without restrictions is also against policy.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Submit an application to Microsoft for access to custom neural voice and wait for approval.
Why this is correct
Access to custom neural voice is restricted. You must submit an application to Microsoft that describes your use case and how you will comply with responsible AI guidelines. Microsoft reviews the application and grants access only if approved. This is a mandatory step before you can create and deploy a CNV model. It ensures that the technology is used responsibly.
- ✗
Deploy the model to a public endpoint without any access restrictions.
Why it's wrong here
Deploying a CNV model to a public endpoint without restrictions is not allowed. Microsoft requires that CNV models be deployed with limited access to prevent misuse. You must implement access controls, such as restricting who can use the voice. This is part of the responsible AI requirements. A public endpoint would violate these requirements.
- ✗
Train the model using data from publicly available audio sources without consent.
Why it's wrong here
Training a CNV model with publicly available audio without consent violates responsible AI principles and Microsoft's requirements. You must have explicit consent from the voice talent. Using data without consent is unethical and against policy. This would result in the model being rejected and could lead to legal issues.
- ✓
Obtain explicit consent from the voice talent and store the consent statement.
Why this is correct
Microsoft requires explicit consent from the voice talent for custom neural voice. You must obtain a signed consent statement and store it. This is part of the gated access process for CNV. The consent ensures that the voice talent understands and agrees to the use of their voice. Without this, the model cannot be approved for deployment.
- ✗
Use a standard voice model instead of a custom neural voice to avoid the approval process.
Why it's wrong here
Using a standard voice model does not meet the requirement for a custom neural voice. The scenario specifies deploying a CNV model. Standard voices are pre-built and do not require the same approval process, but they do not provide a custom voice. This option does not satisfy the need to deploy a CNV model.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.