Text translation is a cloud-based REST API feature of the Translator service that uses neural machine translation technology to enable quick and accurate source-to-target text translation in real time across all supported languages.
The following methods are supported by the Text Translation feature:
Languages. Returns a list of languages supported by Translate, Transliterate, and Dictionary Lookup operations.
Translate. Renders single source-language text to multiple target-language texts with a single request.
Transliterate. Converts characters or letters of a source language to the corresponding characters or letters of a target language.
Detect. Returns the source code language code and a boolean variable denoting whether the detected language is supported for text translation and transliteration.
Dictionary lookup. Returns equivalent words for the source term in the target language.
Dictionary example Returns grammatical structure and context examples for the source term and target term pair.
Please rely heavily on our REST client docs to use this library
Key links:
- LTS versions of Node.js
- Latest versions of Edge, Chrome, Safar and Firefox
- An existing Translator service or Cognitive Services resource.
Install the Azure Text Translation REST client library for JavaScript with npm:
npm install @azure-rest/ai-translation-textYou can create Translator resource following Create a Translator resource.
To use this client library in the browser, first you need to use a bundler. For details on how to do this, please refer to our bundling documentation.
Interaction with the service using the client library begins with creating an instance of the TextTranslationClient class. You will need an API key or TokenCredential to instantiate a client object. For more information regarding authenticating with cognitive services, see Authenticate requests to Translator Service.
You can get the endpoint, API key and Region from the Cognitive Services resource or Translator service resource information in the Azure Portal.
Alternatively, use the Azure CLI snippet below to get the API key from the Translator service resource.
az cognitiveservices account keys list --resource-group <your-resource-group-name> --name <your-resource-name>Once you have the value for the API key and Region, create an TranslatorCredential.
With the value of the TranslatorCredential you can create the TextTranslationClient:
const translateCedential = new TranslatorCredential(apiKey, region);
const translationClient = TextTranslationClient(endpoint, translateCedential);The following section provides several code snippets using the client created above, and covers the main features present in this client library.
Gets the set of languages currently supported by other operations of the Translator.
const langResponse = await translationClient.path("/languages").get();
if (isUnexpected(langResponse)) {
throw langResponse.body;
}
const languages = langResponse.body;
if (languages.translation) {
console.log("Translated languages:");
for (const key in languages.translation) {
const translationLanguage = languages.translation[key];
console.log(`${key} -- name: ${translationLanguage.name} (${translationLanguage.nativeName})`);
}
}
if (languages.transliteration) {
console.log("Transliteration languages:");
for (const key in languages.transliteration) {
const transliterationLanguage = languages.transliteration[key];
console.log(
`${key} -- name: ${transliterationLanguage.name} (${transliterationLanguage.nativeName})`
);
}
}
if (languages.dictionary) {
console.log("Dictionary languages:");
for (const key in languages.dictionary) {
const dictionaryLanguage = languages.dictionary[key];
console.log(
`${key} -- name: ${dictionaryLanguage.name} (${dictionaryLanguage.nativeName}), supported target languages count: ${dictionaryLanguage.translations.length}`
);
}
}Please refer to the service documentation for a conceptual discussion of languages.
Renders single source-language text to multiple target-language texts with a single request.
const inputText = [{ text: "This is a test." }];
const parameters = {
to: "cs",
from: "en",
};
const translateResponse = await translationClient.path("/translate").post({
body: inputText,
queryParameters: parameters,
});
if (isUnexpected(translateResponse)) {
throw translateResponse.body;
}
const translations = translateResponse.body;
for (const translation of translations) {
console.log(
`Text was translated to: '${translation?.translations[0]?.to}' and the result is: '${translation?.translations[0]?.text}'.`
);
}Please refer to the service documentation for a conceptual discussion of translate.
Converts characters or letters of a source language to the corresponding characters or letters of a target language.
const inputText = [{ text: "这是个测试。" }];
const parameters = {
language: "zh-Hans",
fromScript: "Hans",
toScript: "Latn",
};
const transliterateResponse = await translationClient.path("/transliterate").post({
body: inputText,
queryParameters: parameters,
});
if (isUnexpected(transliterateResponse)) {
throw transliterateResponse.body;
}
const translations = transliterateResponse.body;
for (const transliteration of translations) {
console.log(
`Input text was transliterated to '${transliteration?.script}' script. Transliterated text: '${transliteration?.text}'.`
);
}Please refer to the service documentation for a conceptual discussion of transliterate.
Identifies the positioning of sentence boundaries in a piece of text.
const inputText = [{ text: "zhè shì gè cè shì。" }];
const parameters = {
language: "zh-Hans",
script: "Latn",
};
const breakSentenceResponse = await translationClient.path("/breaksentence").post({
body: inputText,
queryParameters: parameters,
});
if (isUnexpected(breakSentenceResponse)) {
throw breakSentenceResponse.body;
}
const breakSentences = breakSentenceResponse.body;
for (const breakSentence of breakSentences) {
console.log(`The detected sentece boundaries: '${breakSentence?.sentLen.join(", ")}'.`);
}Please refer to the service documentation for a conceptual discussion of break sentence.
Returns equivalent words for the source term in the target language.
const inputText = [{ text: "fly" }];
const parameters = {
to: "es",
from: "en",
};
const dictionaryResponse = await translationClient.path("/dictionary/lookup").post({
body: inputText,
queryParameters: parameters,
});
if (isUnexpected(dictionaryResponse)) {
throw dictionaryResponse.body;
}
const dictionaryEntries = dictionaryResponse.body;
for (const dictionaryEntry of dictionaryEntries) {
console.log(
`For the given input ${dictionaryEntry?.translations?.length} entries were found in the dictionary.`
);
console.log(
`First entry: '${dictionaryEntry?.translations[0]?.displayTarget}', confidence: ${dictionaryEntry?.translations[0]?.confidence}.`
);
}Please refer to the service documentation for a conceptual discussion of dictionary lookup.
Returns grammatical structure and context examples for the source term and target term pair.
const inputText = [{ text: "fly", translation: "volar" }];
const parameters = {
to: "es",
from: "en",
};
const dictionaryResponse = await translationClient.path("/dictionary/examples").post({
body: inputText,
queryParameters: parameters,
});
if (isUnexpected(dictionaryResponse)) {
throw dictionaryResponse.body;
}
const dictionaryExamples = dictionaryResponse.body;
for (const dictionaryExample of dictionaryExamples) {
console.log(
`For the given input ${dictionaryExample?.examples?.length} examples were found in the dictionary.`
);
const firstExample = dictionaryExample?.examples[0];
console.log(
`Example: '${firstExample.targetPrefix + firstExample.targetTerm + firstExample.targetSuffix}'.`
);
}Please refer to the service documentation for a conceptual discussion of dictionary examples.
When you interact with the Translator Service using the TextTranslator client library, errors returned by the Translator service correspond to the same HTTP status codes returned for REST API requests.
For example, if you submit a translation request without a target translate language, a 400 error is returned, indicating "Bad Request".
You can find the different error codes returned by the service in the Service Documentation.
Enabling logging may help uncover useful information about failures. In order to see a log of HTTP requests and responses, set the AZURE_LOG_LEVEL environment variable to info. Alternatively, logging can be enabled at runtime by calling setLogLevel in the @azure/logger:
const { setLogLevel } = require("@azure/logger");
setLogLevel("info");For more detailed instructions on how to enable logs, you can look at the @azure/logger package docs.