Azure AI Translator Service

Quick Answer: Azure AI Translator provides text translation (130+ languages), document translation (preserving formatting), and custom translator (domain-specific models). The REST API supports real-time translation, transliteration, dictionary lookup, and automatic language detection.

Text Translation

Basic Translation API Call

import requests
import uuid

endpoint = "https://api.cognitive.microsofttranslator.com"
path = "/translate"
params = {
    "api-version": "3.0",
    "from": "en",
    "to": ["fr", "de", "es"]
}

headers = {
    "Ocp-Apim-Subscription-Key": "<your-key>",
    "Ocp-Apim-Subscription-Region": "eastus",
    "Content-Type": "application/json",
    "X-ClientTraceId": str(uuid.uuid4())
}

body = [{"text": "Hello, how are you?"}]

response = requests.post(
    endpoint + path,
    params=params,
    headers=headers,
    json=body
)

for translation in response.json()[0]["translations"]:
    print(f"{translation['to']}: {translation['text']}")
# Output:
# fr: Bonjour, comment allez-vous?
# de: Hallo, wie geht es Ihnen?
# es: Hola, como estas?

On the Exam: Note that the Translator API uses a different endpoint pattern than other Azure AI services. It uses api.cognitive.microsofttranslator.com with a subscription key AND region header. Also note the to parameter accepts an array for multi-language translation in a single call.

Key API Operations

Transliteration

# Convert Japanese text from kanji to Latin script
params = {
    "api-version": "3.0",
    "language": "ja",
    "fromScript": "jpan",
    "toScript": "latn"
}

body = [{"text": "こんにちは"}]
response = requests.post(
    endpoint + "/transliterate",
    params=params,
    headers=headers,
    json=body
)
# Output: "konnichiha"

Document Translation

Document translation translates entire documents while preserving formatting:

Supported Formats

Document Translation Workflow

1. Upload source documents to Azure Blob Storage (source container)
2. Create a target container for translated documents
3. Generate SAS tokens for both containers
4. Submit a batch translation request
5. Poll for status until translation completes
6. Download translated documents from the target container

Custom Translator

Custom Translator improves translation quality for domain-specific content:

Using a Custom Model

params = {
    "api-version": "3.0",
    "from": "en",
    "to": "fr",
    "category": "my-custom-category-id"  # Custom model
}

On the Exam: Custom Translator questions typically test whether you know the minimum data requirements (10,000 parallel sentences), how to deploy a custom model (category ID), and how to evaluate quality (BLEU score).