Text and Speech Solutions

Objective 2.2, inside the Microsoft Foundry implementation skill area that carries 55–60% of the exam. Two services do most of the work here — Azure Language and Azure Speech in Foundry Tools — and the exam keeps asking the same underlying question: is this a job for a purpose-built feature, or for a model?

Azure Language in Foundry Tools

Azure Language is the text service. You send it text, it sends back structured findings — typed, scored, and consistent. It does not write prose, and that predictability is exactly why it still exists alongside generative models.

Microsoft now splits its features into two tiers, and the distinction confuses people, so be precise about it.

TierFeaturesWhat the tier means
CorePII detection, language detection, named entity recognition (prebuilt and custom), text analytics for healthActively evolving. New capability lands here.
LegacySentiment analysis and opinion mining, key phrase extraction, summarization, entity linking, conversational language understanding, question answering, custom text classificationFully supported and working. Not receiving new investment.
Legacy does not mean retired

This trips people up badly. “Legacy” here means Microsoft is not adding new capability — it does not mean deprecated, retired, or wrong. The exam objective names “keyword extraction, entity detection, sentiment analysis, and summarization” explicitly, and three of those four are in the legacy tier. They are still correct answers. Do not eliminate a choice because you remember the word legacy.

What each feature actually returns

FeatureReturnsExample scenario
Key phrase extractionA flat list of the main talking points, as phrasesSummarize what a thousand survey comments are about, without reading them
Named entity recognitionTyped spans: person, location, organization, datetime, quantity, and morePull every company and date mentioned across a set of news articles
PII detectionDetected personal information, with the option to redact itStrip customer identifiers out of support transcripts before analysis
Sentiment analysisPositive, negative, neutral, or mixed, with confidence scoresTrack how review tone shifts after a product change
Opinion miningSentiment tied to a specific aspect, not just the whole documentLearn that guests like the room but dislike the check-in process
Language detectionThe detected language and a confidence scoreRoute incoming messages to the right regional team
SummarizationA shorter version of the text, extractive or abstractiveGive agents a two-line recap at the top of a long ticket
Text analytics for healthMedical entities, relations, and assertionsExtract medications and dosages from clinical notes
Conversational language understandingAn intent plus entities from a user utteranceWork out that “book me a flight to Seattle Friday” means BookFlight
Question answeringAn answer drawn from a knowledge base of question-and-answer pairsAnswer common questions from an existing FAQ page

Two distinctions the exam leans on

Key phrases versus entities

Key phrases are the main talking points, returned as a plain list. Nothing is typed or categorized.

Entities are typed things — this span is a person, that one is a date. If the question mentions categories, types, or “identify all the organizations,” it wants entity recognition.

Extractive versus abstractive

Extractive summarization selects the most important sentences that already exist, unchanged. Nothing is invented, and every word traces back to the source.

Abstractive summarization writes new sentences that capture the meaning. It can paraphrase and condense across the whole document. If a scenario needs a summary in the reader’s own words, it is abstractive.

Azure Speech in Foundry Tools

Azure Speech handles audio in both directions: turning speech into text, and turning text into speech. It is deterministic, low latency, and built for production audio pipelines.

CapabilityInputOutputExample scenario
Speech to text (real-time)Streaming audioText, as it is spokenLive captions during a meeting
Batch transcriptionMany stored audio filesText, asynchronouslyTranscribe last month’s call recordings overnight
Fast transcriptionA pre-recorded fileText, quicklyTurn an uploaded voicemail into text while the user waits
Custom speechAudio plus your own training dataText, tuned to your vocabularyRecognize product names and industry jargon reliably
Text to speechTextNatural neural-voice audioRead confirmation details back to a caller
SSMLMarked-up textAudio with controlled pronunciation, pace, and emphasisMake the system say a product name correctly every time
Custom neural voiceRecorded voice samples (gated)A brand-specific synthetic voiceOne consistent voice across every customer touchpoint
Speech translationSpoken audio in one languageText or speech in anotherLet a support agent and a caller speak different languages
Speaker recognitionAudio plus enrolled voice profilesWho is speaking, or whether they are who they claimVerify a caller by voice before discussing an account
Pronunciation assessmentLearner audioAccuracy and fluency scoringGive feedback in a language-learning app
Language identificationAudioWhich language is being spokenPick the right transcription model automatically
Voice LiveStreaming conversationLow-latency spoken interactionA natural, interruptible voice assistant
Speaker recognition is not speech recognition

These sound almost identical and mean completely different things. Speech recognition answers what was said and produces a transcript. Speaker recognition answers who said it and is used for identification and verification. Any scenario about confirming a caller’s identity by voice is speaker recognition, no matter how much transcription is also happening.

Responding to spoken prompts with a multimodal model

The objective says “respond to spoken prompts by using a deployed multimodal model,” and that is a different thing from the Speech service. The realtime and audio model families in Foundry Models take speech in and produce speech out, with a language model reasoning in between. There is no separate transcribe step you manage, no separate synthesis step, and crucially the model understands and answers rather than just converting formats.

Azure SpeechMultimodal audio model
What it doesConverts between audio and textUnderstands spoken input and answers it
ReasoningNone — it is a converterFull language model reasoning between input and output
OutputA transcript, or synthesized audio you supplied the words forA spoken answer the model composed itself
Reach for it whenYou need an accurate transcript, a branded voice, or speaker verificationYou want a conversational assistant that listens and replies

Whisper also appears in Foundry Models as a transcription model. It converts speech to text; it does not hold a conversation.

Purpose-built feature or generative model?

This is the decision the exam returns to again and again, in both directions. Neither answer is always right, and the scenario always contains the deciding constraint.

SituationBetter choiceWhy
Output must be consistently structured and typedPurpose-built featureIt returns the same shape every time. A model may phrase things differently on each call.
High volume, latency and cost matterPurpose-built featureNarrow models are faster and cheaper per call than general-purpose ones.
Regulated domain needing predictable behaviorPurpose-built featureDocumented, auditable behavior is easier to defend than free-form generation.
Clinical or medical textText analytics for healthPurpose-built for medical entities, relations, and assertions.
Detecting and redacting personal informationPII detectionBuilt for exactly this, with redaction included.
Verbatim transcription, or a branded voiceAzure SpeechDeterministic transcription, custom neural voice, and SSML control live here.
Confirming who is speakingAzure Speech speaker recognitionNo generative model does voice identity.
The task is novel, or combines several steps in one callGenerative modelOne prompt can summarize, classify, and rewrite together.
The task needs reasoning about the contentGenerative modelPurpose-built features detect and label; they do not reason.
Input mixes text with images or audioMultimodal modelPurpose-built text features only take text.
A spoken, conversational assistantMultimodal audio modelSpeech in, reasoning, speech out, in one model.

Azure Translator in Foundry Tools

Translator is the third service in this objective and the one people misplace most often. It does text translation between languages, document translation that preserves formatting, and transliteration.

Two Translator rules worth memorizing

Text translation lives in Translator; spoken translation lives in Azure Speech. If the input is audio, the answer is Speech, even though the task is translation.

Transliteration is not translation. It rewrites text from one script into another — Hindi written in Latin characters, for example. The language does not change, only the alphabet. A question about making a name readable in another script wants transliteration.

Where people lose points

The mistakeWhat is actually true
Eliminating sentiment analysis or key phrase extraction because they are “legacy”Legacy means no new investment, not retired. The objective names these features explicitly and they remain correct answers.
Answering key phrase extraction when the scenario asks for typesCategories such as person, location, or organization mean named entity recognition.
Treating extractive and abstractive summarization as interchangeableExtractive selects existing sentences; abstractive writes new ones. Scenarios that need paraphrasing are abstractive.
Choosing speech recognition for a caller-identity scenarioIdentity by voice is speaker recognition. Speech recognition only produces the transcript.
Sending audio to Azure TranslatorTranslator takes text. Spoken translation is Azure Speech.
Calling transliteration a kind of translationTransliteration changes the script, not the language.
Reaching for a generative model for everythingWhen the scenario stresses consistent structure, latency, cost, or compliance, the purpose-built feature is the better answer.
Reaching for a purpose-built feature for everythingWhen the task is novel, needs reasoning, or combines steps, a model wins.
Confusing question answering with conversational language understandingA knowledge base of question-and-answer pairs means question answering. Working out intent from a free-form utterance means conversational language understanding.

The night-before cheat sheet

Azure Language, one line each

  • Key phrases — the main talking points, untyped
  • Entities — typed things: person, place, org, date
  • PII detection — find and redact personal data
  • Sentiment — positive, negative, neutral, mixed
  • Opinion mining — sentiment about a specific aspect
  • Language detection — which language is this
  • Summarization — extractive selects, abstractive rewrites
  • Health — medical entities and relations
  • CLU — intent plus entities from an utterance
  • Question answering — answers from a knowledge base

Azure Speech, one line each

  • Speech to text — real-time, batch, or fast
  • Custom speech — tuned to your vocabulary
  • Text to speech — neural voices
  • SSML — control pronunciation and pace
  • Custom neural voice — brand voice, gated
  • Speech translation — spoken, across languages
  • Speaker recognitionwho is talking
  • Voice Live — low-latency conversation

The decisions, in one line each

  • Core versus legacy — legacy still works and is still the right answer when the objective names it.
  • Key phrases versus entities — types and categories mean entities.
  • Extractive versus abstractive — selects existing sentences versus writes new ones.
  • Speech versus speaker — what was said versus who said it.
  • Translator versus Speech — text in, or audio in.
  • Transliteration — new script, same language.
  • Purpose-built versus generative — consistency, latency, cost, and compliance point to purpose-built; novelty, reasoning, and combined steps point to a model.
  • Speech service versus multimodal audio model — converting formats versus understanding and answering.