Implementing Multilingual Support with Amazon Translate - Real-Time Translation and Custom Terminology
Learn about real-time translation with Translate, improving translation quality with custom terminology, and leveraging batch translation for large-scale document processing.
Translate Overview
Translate is a service that provides neural machine translation across 75+ languages, and real-time translation accepts up to 10,000 bytes of input text per request. The real-time translation API (TranslateText) is a synchronous call that returns results, making it suitable for integration with chat and web forms. The response includes automatic source language detection in addition to translated text, allowing it to handle cases where the input language is unknown. Batch translation (StartTextTranslationJob) executes bulk translation of large document volumes as asynchronous jobs, using S3 as storage. Two translation modes are available - Standard and Active Custom Translation - allowing you to balance accuracy and cost based on your use case.
Custom Terminology and Batch Translation
Custom terminology defines term pairs in CSV or TMX format, so that specified terms are reflected in translations. This lets you control translations such as preventing the product name "Amazon Aurora" from being translated and keeping it in its original form. You can create up to 100 custom terminology files per account per Region, with a maximum size of 20 MB per file. Custom terminology lets you define different mappings per translation direction, such as applying different translations for Japanese-to-English versus English-to-Japanese. Batch translation places documents in an S3 bucket input folder and stores translation results in an output folder. It supports HTML, DOCX, XLIFF, PowerPoint, and Excel formats, preserving tag structure during translation. The volume a batch job can process and the number of concurrent jobs are limited by quotas.
Parallel Data and Active Custom Translation
Parallel data (parallel corpora) provides source and translation text pairs in CSV or TMX format, adapting the translation model to domain-specific expressions. Translation quality can be expected to improve in fields with heavy specialized terminology, such as technical documentation, legal documents, and medical documents. Active Custom Translation (ACT) uses parallel data to adjust translations, generating context-aware output. How much effect you see depends on the amount of parallel data. Profanity masking automatically detects inappropriate expressions and masks or excludes them. Formality settings let you control the formality level (polite/casual) of translations, allowing you to use appropriate tones for business documents versus casual chat. Supported languages for Formality are limited to Japanese, German, French, Italian, Portuguese, and others, so verify support for your target language pair in advance.
Use Cases and Architecture Patterns
Translate applies to a wide range of workloads. For multilingual e-commerce product descriptions, you can build a serverless pipeline using EventBridge + Lambda + Translate that auto-translates on new product registration and stores results in DynamoDB. In customer support, combining it with Amazon Connect enables real-time chat message translation so agents and users can converse in different languages. For knowledge base localization, batch translation processes technical documents stored in S3, and Amazon Kendra provides multilingual search. In social media monitoring, a real-time pipeline receives posts via Kinesis Data Streams, unifies text to English with Translate, then runs sentiment analysis with Comprehend.
Comparison with Other Translation Services
Translate's strength lies in its integration with the AWS ecosystem. It supports fine-grained access control via IAM, API auditing via CloudTrail, and private connectivity via VPC endpoints, helping address enterprise security requirements. One of Translate's features is parallel data adaptation with ACT. When comparing Translate with other translation services such as DeepL API, look at the supported language pairs and the languages supported for Formality. Compared to on-premises neural translation, Translate eliminates GPU infrastructure management and automates scaling. However, weakness in literary expressions and idioms is a common challenge across all cloud translation services.
Translate Pricing
Translate pricing is based on the number of characters translated. Batch translation is also billed by characters and allows bulk processing of large document volumes via S3. Under the legacy 12-month free tier (accounts created before July 15, 2025), 2 million characters per month were included (accounts created after that date use the credit-based free plan of up to $200 in credits; see the official AWS site for current terms). There is no additional charge for using custom terminology. You can optimize costs by pre-stripping HTML tags and metadata from translation targets to reduce non-translatable character counts. Adding a caching layer to avoid re-translating identical text is also effective.
Summary
Translate is a service that enables multilingual support across 75+ languages using neural machine translation. Custom terminology controls the translation of product names and specialized terms, while Active Custom Translation provides domain adaptation through parallel data. Formality settings let you switch between polite and casual tones, and batch translation automates the multilingual conversion of large content volumes. Integration with the AWS ecosystem supports use cases such as serverless auto-translation pipelines and real-time chat translation.
References (Official AWS Resources)
The primary sources for this page are the official AWS website and documentation. Check the official pages below for the latest specifications and pricing.
- Amazon Translate official page
- Amazon S3 official page
- AWS Lambda official page
- AWS Documentation (official)
If this page and the official documentation disagree, treat the official documentation as authoritative.