AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
A media company is building a knowledge mining solution with Azure AI Search. They need to enrich video assets by extracting spoken words from the audio track and then indexing that transcript for search. Which two components must be included in the enrichment pipeline? (Choose two.)
⚠ Common exam trap
The trap here is assuming Azure AI Search has a built-in skill for audio transcription, when video or speech transcription must be handled by a custom skill.
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
✓
A custom skill that calls Azure AI Video Indexer or the Speech service to transcribe the audio.
To index spoken words from video, the pipeline needs a data source and indexer to pull video assets from Blob Storage, plus a custom skill that calls a speech-to-text service because Azure AI Search has no built-in audio transcription skill. OCR, synonym maps, and scoring profiles operate on images, queries, or ranking respectively and cannot produce a transcript.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
A custom skill that calls Azure AI Video Indexer or the Speech service to transcribe the audio.
Why this is correct
Azure AI Search does not include a built-in skill that transcribes video audio, so a custom skill is required to invoke a speech-to-text service such as Azure AI Video Indexer or the Speech service. The custom skill returns the transcript as enriched text that can then be mapped into an index field for search.
- ✗
A scoring profile that boosts video documents by duration.
Why it's wrong here
Scoring profiles influence relevance ranking of search results based on index fields; they do not extract or generate transcripts. A duration-based boost changes result ordering but leaves the video content unindexed. It is unrelated to the requirement to transcribe and index spoken words.
- ✓
An indexer configured for Azure Blob Storage with the video files in a container.
Why this is correct
The indexer is the component that crawls the data source, in this case an Azure Blob Storage container holding the video files, and feeds documents into the enrichment pipeline. Without an indexer pointed at the video assets, no documents would flow through the skillset, so the transcript could never be generated or indexed.
- ✗
A synonym map that maps spoken words to their text equivalents.
Why it's wrong here
A synonym map expands query terms at search time; it does not transcribe audio or create text from video. It operates on queries against an index, not on enrichment of source documents. Including one would not help extract spoken words from video assets, so it fails the requirement.
- ✗
A skillset entry that calls the built-in OCR skill on the video file.
Why it's wrong here
OCR extracts text from images and embedded images in documents or PDFs, not from audio tracks in video files. Applying it to a video asset would not produce a transcript of spoken words. It is the wrong extraction modality for the requirement, so it does not contribute to indexing spoken content.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.