Amazon Translate
Fully managed neural machine translation for text, across 75 languages.
Verified against AWS documentation · 2026-08-24
Key facts
- 01Text in, text out — source language is either declared or set to `auto` (which calls Comprehend behind the scenes)
- 02Two modes: real-time (TranslateText, TranslateDocument) and asynchronous batch over an S3 folder
- 03Customization without training a model: custom terminology pins individual terms, parallel data (ACT) steers domain and style
- 04Limits: 10,000 bytes per real-time text call, 100 KB per real-time document, 20 MB per batch document
Exam triggers
Phrases and scenarios that point here.
- "Translate", "localize", "multilingual", "in the customer's preferred language"
- Thousands of documents already sitting in S3 → batch translation job, not a loop of real-time calls
- Brand or product names must survive untranslated → custom terminology
- Audio anywhere in the requirement → Transcribe before, Polly after — Translate only handles text
Not this service
- Speech to text → Amazon Transcribe. Text to speech → Amazon Polly
- Detect language, sentiment, or entities without translating → Amazon Comprehend
Use cases
- 01Localizing a support knowledge base: nightly batch job reads an S3 prefix of HTML articles, writes translated copies to an output prefix in ten target languages — the job runs under an IAM data access role, not the caller's credentials
- 02Live agent chat where the rep types English and the customer reads Thai — a single TranslateText call sits inline in the message path, fast enough that neither side notices
- 03Normalizing multilingual product reviews to English before analytics, so the sentiment pipeline downstream only ever has to reason about one language
- 04Subtitle pipelines: Transcribe produces the transcript, Translate produces the caption tracks, Polly optionally voices them — three services, one chain
- 05Catalogue localization where custom terminology locks model names, SKUs, and legal disclaimers so "Nimbus Pro" never ships as "Cloud Professional"
How it's charged
- 01Priced per character of input, including whitespace and any markup left in the request — batching saves nothing, stripping HTML does
- 02Standard text translation (real-time and batch) is one flat per-character rate; Active Custom Translation costs several times more per character
- 03Custom terminology is free to use — the paid customization path is parallel data / ACT
- 04Auto language detection invokes Amazon Comprehend on your behalf and is billed accordingly; passing a known source language code avoids that charge
- 05Free tier covers 2 million characters per month for the first 12 months on standard text translation; re-translating the same static UI strings is billed every time, so cache them
