4.4 Azure AI Translator Service
Key Takeaways
- Azure AI Translator provides real-time text translation between 100+ languages using neural machine translation.
- The service supports text translation (translate written text), document translation (translate entire documents preserving formatting), and custom translator (train domain-specific models).
- Transliteration converts text from one script to another (e.g., Japanese Kanji to Latin characters) without changing the language.
- Custom Translator lets you build domain-specific translation models using your own parallel text (bilingual documents) for higher accuracy in specialized fields.
- Azure AI Translator is separate from Azure AI Speech translation — Translator handles text; Speech handles spoken audio.
Azure AI Translator Service
Quick Answer: Azure AI Translator provides text translation for 100+ languages, document translation (preserving formatting), transliteration (script conversion), and Custom Translator for domain-specific models. It is different from speech translation — Translator handles text, Speech handles audio.
What Is Azure AI Translator?
Azure AI Translator is a cloud-based machine translation service that enables real-time text translation between more than 100 languages. It uses neural machine translation (NMT) technology for natural, fluent translations.
Core Capabilities
1. Text Translation
Translate text from one language to another:
| Feature | Description |
|---|---|
| Languages | 100+ supported languages |
| Auto-detect source | Automatically identify the source language |
| Multi-target | Translate to multiple languages in one request |
| HTML support | Translate HTML content while preserving tags |
| Profanity handling | Options to mark, delete, or ignore profanity |
2. Document Translation
Translate entire documents while preserving their original formatting:
| Feature | Description |
|---|---|
| Supported formats | PDF, DOCX, PPTX, XLSX, HTML, TXT, and more |
| Formatting preserved | Tables, images, headers, and layout maintained |
| Batch translation | Translate multiple documents in one operation |
| Glossary support | Use custom glossaries for consistent terminology |
3. Transliteration
Convert text from one script to another WITHOUT changing the language:
Example:
- Japanese (Kanji): 東京 → Japanese (Latin): Tōkyō
- Arabic: مرحبا → Arabic (Latin): mrhba
- Hindi (Devanagari): नमस्ते → Hindi (Latin): namaste
This is useful for reading text in unfamiliar scripts.
4. Custom Translator
Build domain-specific translation models for higher accuracy in specialized fields:
| Step | Description |
|---|---|
| Upload parallel data | Provide bilingual document pairs (source + translation) |
| Train custom model | The service learns your domain's terminology and style |
| Test and evaluate | Compare custom model to generic model |
| Deploy | Use your custom model for translations |
When to use Custom Translator:
- Legal documents with specific legal terminology
- Medical content with specialized medical vocabulary
- Technical documentation with product-specific terms
- Any domain where generic translation misses nuances
Translator vs. Speech Translation
| Aspect | Azure AI Translator | Azure AI Speech Translation |
|---|---|---|
| Input | Written text | Spoken audio |
| Output | Translated text | Translated text or speech |
| Use case | Translate documents, web pages, text | Translate live conversations |
| Real-time | Yes | Yes |
| API | Translator API | Speech SDK |
On the Exam: If the question involves translating WRITTEN text or documents, the answer is Azure AI Translator. If the question involves translating SPOKEN audio in real-time conversations, the answer is Azure AI Speech translation.
A company needs to translate their product documentation from English into 15 different languages while preserving the original formatting (tables, headers, images). Which Azure service should they use?
What is transliteration?
When should you use Custom Translator instead of the standard Azure AI Translator?