Select your cookie preferences

We use essential cookies and similar tools that are necessary to provide our site and services. We use performance cookies to collect anonymous statistics, so we can understand how customers use our site and make improvements. Essential cookies cannot be deactivated, but you can choose “Customize” or “Decline” to decline performance cookies.

If you agree, AWS and approved third parties will also use cookies to provide useful site features, remember your preferences, and display relevant content, including relevant advertising. To accept or decline all non-essential cookies, choose “Accept” or “Decline.” To make more detailed choices, choose “Customize.”

Using custom terminologies

Focus mode
Using custom terminologies - Amazon Translate

To use a Custom Terminology when translating text with the TranslateText operation, include the optional TerminologyNames parameter.

For example, if you upload the following terminology file called Amazon_Family.csv to your account:

en,fr Amazon Family,Amazon Famille

You can use the following CLI command to translate your text using Custom Terminology.

Note

This example is formatted for Unix, Linux, and macOS. For Windows, replace the backslash (\) Unix continuation character at the end of each line with a caret (^).

aws translate translate-text \ --region region \ --source-language-code "en" \ --target-language-code "fr" \ --terminology-names "Amazon_Family" \ --text "Have you ever stored videos in Amazon Family?"

This uses the selected Custom Terminology to translate this text as "Avez-vous déjà fait des achats avec Amazon Famille?" instead of the direct (but undesirable) translation "Avez-vous déjà fait des achats avec Famille Amazon?"

The following example shows how to use the same terminology file in Python.

import boto3 translate = boto3.client(service_name='translate') print("Translating 'Have you ever shopped with Amazon Family?' from English to French with the 'Amazon_Family' custom terminology...") response = translate.translate_text(Text="Have you ever shopped with Amazon Family?", TerminologyNames=["Amazon_Family"], SourceLanguageCode="en", TargetLanguageCode="fr") print("Translated text: " + response.get('TranslatedText')) print("\n")

For more information on using the Amazon Translate operations with Custom Terminologies, see API Operations.

PrivacySite termsCookie preferences
© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved.