Use Azure AI Translator APIs

  • Article

In this how-to guide, you learn to use the Translator service REST APIs. You start with basic examples and move onto some core configuration options that are commonly used during development, including:

Prerequisites

  • Azure subscription - Create one for trial

  • An Azure AI multi-service or Translator resource. Once you have your Azure subscription, create a single-service or a multi-service resource, in the Azure portal, to get your key and endpoint. After it deploys, select Go to resource.

  • You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.

  • You need the key and endpoint from the resource to connect your application to the Translator service. Later, you paste your key and endpoint into the code samples. You can find these values on the Azure portal Keys and Endpoint page:

    Screenshot: Azure portal keys and endpoint page.

Important

Remember to remove the key from your code when you're done, and never post it publicly. For production, use a secure way of storing and accessing your credentials like Azure Key Vault. For more information, see the Azure AI services security.

Headers

To call the Translator service via the REST API, you need to make sure the following headers are included with each request. Don't worry, we include the headers in the sample code in the following sections.

Header Value Condition
Ocp-Apim-Subscription-Key Your Translator service key from the Azure portal.
  • Required
Ocp-Apim-Subscription-Region The region where your resource was created.
  • Required when using an Azure AI multi-service or regional (geographic) resource like China North.
  • Optional when using a single-service Translator Resource.
Content-Type The content type of the payload. The accepted value is application/json or charset=UTF-8.
  • Required
Content-Length The length of the request body.
  • Optional
X-ClientTraceId A client-generated GUID to uniquely identify the request. You can omit this header if you include the trace ID in the query string using a query parameter named ClientTraceId.
  • Optional

Set up your application

  1. Make sure you have the current version of Visual Studio IDE.

    Tip

    If you're new to Visual Studio, try the Introduction to Visual Studio Learn module.

  2. Open Visual Studio.

  3. On the Start page, choose Create a new project.

    Screenshot: Visual Studio start window.

  4. On the Create a new project page, enter console in the search box. Choose the Console Application template, then choose Next.

    Screenshot: Visual Studio's create new project page.

  5. In the Configure your new project dialog window, enter translator_text_app in the Project name box. Leave the "Place solution and project in the same directory" checkbox unchecked and select Next.

    Screenshot: Visual Studio's configure new project dialog window.

  6. In the Additional information dialog window, make sure .NET 6.0 (Long-term support) is selected. Leave the "Don't use top-level statements" checkbox unchecked and select Create.

    Screenshot: Visual Studio's additional information dialog window.

Install the Newtonsoft.json package with NuGet

  1. Right-click on your translator_quickstart project and select Manage NuGet Packages... .

    Screenshot of the NuGet package search box.

  2. Select the Browse tab and type Newtonsoft.

    Screenshot of the NuGet package install window.

  3. Select install from the right package manager window and add the package to your project.

    Screenshot of the NuGet package install button.

Build your application

Note

  • Starting with .NET 6, new projects using the console template generate a new program style that differs from previous versions.
  • The new output uses recent C# features that simplify the code you need to write.
  • When you use the newer version, you only need to write the body of the Main method. You don't need to include top-level statements, global using directives, or implicit using directives.
  • For more information, see New C# templates generate top-level statements.

  1. Open the Program.cs file.

  2. Delete the pre-existing code, including the line Console.WriteLine("Hello World!"). Copy and paste the code samples into your application's Program.cs file. For each code sample, make sure you update the key and endpoint variables with values from your Azure portal Translator instance.

  3. Once you add a desired code sample to your application, choose the green start button next to formRecognizer_quickstart to build and run your program, or press F5.

Screenshot of the run program button in Visual Studio.

Important

The samples in this guide require hard-coded keys and endpoints. Remember to remove the key from your code when you're done, and never post it publicly. For production, consider using a secure way of storing and accessing your credentials. For more information, see Azure AI services security.

Translate text

The core operation of the Translator service is to translate text. In this section, you build a request that takes a single source (from) and provides two outputs (to). Then we review some parameters that can be used to adjust both the request and the response.

using System.Text;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
    // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // Input and output languages are defined as parameters.
        string route = "/translate?api-version=3.0&from=en&to=sw&to=it";
        string textToTranslate = "Hello, friend! What did you do today?";
        object[] body = new object[] { new { Text = textToTranslate } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            // location required if you're using a multi-service or regional (not global) resource.
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response:

[
   {
      "translations":[
         {
            "text":"Halo, rafiki! Ulifanya nini leo?",
            "to":"sw"
         },
         {
            "text":"Ciao, amico! Cosa hai fatto oggi?",
            "to":"it"
         }
      ]
   }
]

You can check the consumption (the number of characters charged) for each request in the response headers: x-metered-usage field.

Detect language

If you need translation, but don't know the language of the text, you can use the language detection operation. There's more than one way to identify the source text language. In this section, you learn how to use language detection using the translate endpoint, and the detect endpoint.

Detect source language during translation

If you don't include the from parameter in your translation request, the Translator service attempts to detect the source text's language. In the response, you get the detected language (language) and a confidence score (score). The closer the score is to 1.0, means that there's increased confidence that the detection is correct.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
// required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // Output languages are defined as parameters, input language detected.
        string route = "/translate?api-version=3.0&to=en&to=it";
        string textToTranslate = "Halo, rafiki! Ulifanya nini leo?";
        object[] body = new object[] { new { Text = textToTranslate } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            // location required if you're using a multi-service or regional (not global) resource. 
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response:

[
   {
      "detectedLanguage":{
         "language":"sw",
         "score":0.8
      },
      "translations":[
         {
            "text":"Hello friend! What did you do today?",
            "to":"en"
         },
         {
            "text":"Ciao amico! Cosa hai fatto oggi?",
            "to":"it"
         }
      ]
   }
]

Detect source language without translation

It's possible to use the Translator service to detect the language of source text without performing a translation. To do so, you use the /detect endpoint.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
// required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // Just detect language
        string route = "/detect?api-version=3.0";
        string textToLangDetect = "Hallo Freund! Was hast du heute gemacht?";
        object[] body = new object[] { new { Text = textToLangDetect } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

The /detect endpoint response includes alternate detections, and indicates if the translation and transliteration are supported for all of the detected languages. After a successful call, you should see the following response:

[
   {
      "language":"de",

      "score":1.0,

      "isTranslationSupported":true,

      "isTransliterationSupported":false
   }
]

Transliterate text

Transliteration is the process of converting a word or phrase from the script (alphabet) of one language to another based on phonetic similarity. For example, you could use transliteration to convert "สวัสดี" (thai) to "sawatdi" (latn). There's more than one way to perform transliteration. In this section, you learn how to use language detection using the translate endpoint, and the transliterate endpoint.

Transliterate during translation

If you're translating into a language that uses a different alphabet (or phonemes) than your source, you might need a transliteration. In this example, we translate "Hello" from English to Thai. In addition to getting the translation in Thai, you get a transliteration of the translated phrase using the Latin alphabet.

To get a transliteration from the translate endpoint, use the toScript parameter.

Note

For a complete list of available languages and transliteration options, see language support.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
   // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // Output language defined as parameter, with toScript set to latn
        string route = "/translate?api-version=3.0&to=th&toScript=latn";
        string textToTransliterate = "Hello, friend! What did you do today?";
        object[] body = new object[] { new { Text = textToTransliterate } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response. Keep in mind that the response from translate endpoint includes the detected source language with a confidence score, a translation using the alphabet of the output language, and a transliteration using the Latin alphabet.

[
  {
    "detectedLanguage": {
      "language": "en",
      "score": 1
    },
    "translations": [
      {
        "text": "หวัดดีเพื่อน! วันนี้เธอทำอะไรไปบ้าง ",
        "to": "th",
        "transliteration": {
          "script": "Latn",
          "text": "watdiphuean! wannithoethamaraipaiang"
        }
      }
    ]
  }
]

Transliterate without translation

You can also use the transliterate endpoint to get a transliteration. When using the transliteration endpoint, you must provide the source language (language), the source script/alphabet (fromScript), and the output script/alphabet (toScript) as parameters. In this example, we're going to get the transliteration for สวัสดีเพื่อน! วันนี้คุณทำอะไร.

Note

For a complete list of available languages and transliteration options, see language support.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
   // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // For a complete list of options, see API reference.
        // Input and output languages are defined as parameters.
        string route = "/transliterate?api-version=3.0&language=th&fromScript=thai&toScript=latn";
        string textToTransliterate = "สวัสดีเพื่อน! วันนี้คุณทำอะไร";
        object[] body = new object[] { new { Text = textToTransliterate } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            // location required if you're using a multi-service or regional (not global) resource.
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response. Unlike the call to the translate endpoint, transliterate only returns the text and the output script.

[
   {
      "text":"sawatdiphuean! wannikhunthamarai",

      "script":"latn"
   }
]

Get sentence length

With the Translator service, you can get the character count for a sentence or series of sentences. The response is returned as an array, with character counts for each sentence detected. You can get sentence lengths with the translate and breaksentence endpoints.

Get sentence length during translation

You can get character counts for both source text and translation output using the translate endpoint. To return sentence length (srcSenLen and transSenLen) you must set the includeSentenceLength parameter to True.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
   // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // Include sentence length details.
        string route = "/translate?api-version=3.0&to=es&includeSentenceLength=true";
        string sentencesToCount =
                "Can you tell me how to get to Penn Station? Oh, you aren't sure? That's fine.";
        object[] body = new object[] { new { Text = sentencesToCount } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            // location required if you're using a multi-service or regional (not global) resource.
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response. In addition to the detected source language and translation, you get character counts for each detected sentence for both the source (srcSentLen) and translation (transSentLen).

[
   {
      "detectedLanguage":{
         "language":"en",
         "score":1.0
      },
      "translations":[
         {
            "text":"¿Puedes decirme cómo llegar a Penn Station? Oh, ¿no estás seguro? Está bien.",
            "to":"es",
            "sentLen":{
               "srcSentLen":[
                  44,
                  21,
                  12
               ],
               "transSentLen":[
                  44,
                  22,
                  10
               ]
            }
         }
      ]
   }
]

Get sentence length without translation

The Translator service also lets you request sentence length without translation using the breaksentence endpoint.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
   // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // Only include sentence length details.
        string route = "/breaksentence?api-version=3.0";
        string sentencesToCount =
                "Can you tell me how to get to Penn Station? Oh, you aren't sure? That's fine.";
        object[] body = new object[] { new { Text = sentencesToCount } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            // location required if you're using a multi-service or regional (not global) resource.
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response. Unlike the call to the translate endpoint, breaksentence only returns the character counts for the source text in an array called sentLen.

[
   {
      "detectedLanguage":{
         "language":"en",
         "score":1.0
      },
      "sentLen":[
         44,
         21,
         12
      ]
   }
]

Dictionary lookup (alternate translations)

With the endpoint, you can get alternate translations for a word or phrase. For example, when translating the word "sunshine" from en to es, this endpoint returns "luz solar," "rayos solares," and "soleamiento," "sol," and "insolación."

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
   // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // See many translation options
        string route = "/dictionary/lookup?api-version=3.0&from=en&to=es";
        string wordToTranslate = "sunlight";
        object[] body = new object[] { new { Text = wordToTranslate } };
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            // location required if you're using a multi-service or regional (not global) resource.
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response. Let's examine the response more closely since the JSON is more complex than some of the other examples in this article. The translations array includes a list of translations. Each object in this array includes a confidence score (confidence), the text optimized for end-user display (displayTarget), the normalized text (normalizedText), the part of speech (posTag), and information about previous translation (backTranslations). For more information about the response, see Dictionary Lookup

[
   {
      "normalizedSource":"sunlight",
      "displaySource":"sunlight",
      "translations":[
         {
            "normalizedTarget":"luz solar",
            "displayTarget":"luz solar",
            "posTag":"NOUN",
            "confidence":0.5313,
            "prefixWord":"",
            "backTranslations":[
               {
                  "normalizedText":"sunlight",
                  "displayText":"sunlight",
                  "numExamples":15,
                  "frequencyCount":702
               },
               {
                  "normalizedText":"sunshine",
                  "displayText":"sunshine",
                  "numExamples":7,
                  "frequencyCount":27
               },
               {
                  "normalizedText":"daylight",
                  "displayText":"daylight",
                  "numExamples":4,
                  "frequencyCount":17
               }
            ]
         },
         {
            "normalizedTarget":"rayos solares",
            "displayTarget":"rayos solares",
            "posTag":"NOUN",
            "confidence":0.1544,
            "prefixWord":"",
            "backTranslations":[
               {
                  "normalizedText":"sunlight",
                  "displayText":"sunlight",
                  "numExamples":4,
                  "frequencyCount":38
               },
               {
                  "normalizedText":"rays",
                  "displayText":"rays",
                  "numExamples":11,
                  "frequencyCount":30
               },
               {
                  "normalizedText":"sunrays",
                  "displayText":"sunrays",
                  "numExamples":0,
                  "frequencyCount":6
               },
               {
                  "normalizedText":"sunbeams",
                  "displayText":"sunbeams",
                  "numExamples":0,
                  "frequencyCount":4
               }
            ]
         },
         {
            "normalizedTarget":"soleamiento",
            "displayTarget":"soleamiento",
            "posTag":"NOUN",
            "confidence":0.1264,
            "prefixWord":"",
            "backTranslations":[
               {
                  "normalizedText":"sunlight",
                  "displayText":"sunlight",
                  "numExamples":0,
                  "frequencyCount":7
               }
            ]
         },
         {
            "normalizedTarget":"sol",
            "displayTarget":"sol",
            "posTag":"NOUN",
            "confidence":0.1239,
            "prefixWord":"",
            "backTranslations":[
               {
                  "normalizedText":"sun",
                  "displayText":"sun",
                  "numExamples":15,
                  "frequencyCount":20387
               },
               {
                  "normalizedText":"sunshine",
                  "displayText":"sunshine",
                  "numExamples":15,
                  "frequencyCount":1439
               },
               {
                  "normalizedText":"sunny",
                  "displayText":"sunny",
                  "numExamples":15,
                  "frequencyCount":265
               },
               {
                  "normalizedText":"sunlight",
                  "displayText":"sunlight",
                  "numExamples":15,
                  "frequencyCount":242
               }
            ]
         },
         {
            "normalizedTarget":"insolación",
            "displayTarget":"insolación",
            "posTag":"NOUN",
            "confidence":0.064,
            "prefixWord":"",
            "backTranslations":[
               {
                  "normalizedText":"heat stroke",
                  "displayText":"heat stroke",
                  "numExamples":3,
                  "frequencyCount":67
               },
               {
                  "normalizedText":"insolation",
                  "displayText":"insolation",
                  "numExamples":1,
                  "frequencyCount":55
               },
               {
                  "normalizedText":"sunstroke",
                  "displayText":"sunstroke",
                  "numExamples":2,
                  "frequencyCount":31
               },
               {
                  "normalizedText":"sunlight",
                  "displayText":"sunlight",
                  "numExamples":0,
                  "frequencyCount":12
               },
               {
                  "normalizedText":"solarization",
                  "displayText":"solarization",
                  "numExamples":0,
                  "frequencyCount":7
               },
               {
                  "normalizedText":"sunning",
                  "displayText":"sunning",
                  "numExamples":1,
                  "frequencyCount":7
               }
            ]
         }
      ]
   }
]

Dictionary examples (translations in context)

After you perform a dictionary lookup, pass the source and translation text to the dictionary/examples endpoint, to get a list of examples that show both terms in the context of a sentence or phrase. Building on the previous example, you use the normalizedText and normalizedTarget from the dictionary lookup response as text and translation respectively. The source language (from) and output target (to) parameters are required.

using System;
using Newtonsoft.Json; // Install Newtonsoft.Json with NuGet

class Program
{
    private static readonly string key = "<YOUR-TRANSLATOR-KEY>";
    private static readonly string endpoint = "https://api.translator.azure.cn";

    // location, also known as region.
   // required if you're using a multi-service or regional (not global) resource. It can be found in the Azure portal on the Keys and Endpoint page.
    private static readonly string location = "<YOUR-RESOURCE-LOCATION>";

    static async Task Main(string[] args)
    {
        // See examples of terms in context
        string route = "/dictionary/examples?api-version=3.0&from=en&to=es";
        object[] body = new object[] { new { Text = "sunlight",  Translation = "luz solar" } } ;
        var requestBody = JsonConvert.SerializeObject(body);

        using (var client = new HttpClient())
        using (var request = new HttpRequestMessage())
        {
            // Build the request.
            request.Method = HttpMethod.Post;
            request.RequestUri = new Uri(endpoint + route);
            request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
            request.Headers.Add("Ocp-Apim-Subscription-Key", key);
            // location required if you're using a multi-service or regional (not global) resource.
            request.Headers.Add("Ocp-Apim-Subscription-Region", location);

            // Send the request and get response.
            HttpResponseMessage response = await client.SendAsync(request).ConfigureAwait(false);
            // Read response as a string.
            string result = await response.Content.ReadAsStringAsync();
            Console.WriteLine(result);
        }
    }
}

After a successful call, you should see the following response. For more information about the response, see Dictionary Lookup

[
   {
      "normalizedSource":"sunlight",
      "normalizedTarget":"luz solar",
      "examples":[
         {
            "sourcePrefix":"You use a stake, silver, or ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Se usa una estaca, plata, o ",
            "targetTerm":"luz solar",
            "targetSuffix":"."
         },
         {
            "sourcePrefix":"A pocket of ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Una bolsa de ",
            "targetTerm":"luz solar",
            "targetSuffix":"."
         },
         {
            "sourcePrefix":"There must also be ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"También debe haber ",
            "targetTerm":"luz solar",
            "targetSuffix":"."
         },
         {
            "sourcePrefix":"We were living off of current ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Estábamos viviendo de la ",
            "targetTerm":"luz solar",
            "targetSuffix":" actual."
         },
         {
            "sourcePrefix":"And they don't need unbroken ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Y ellos no necesitan ",
            "targetTerm":"luz solar",
            "targetSuffix":" ininterrumpida."
         },
         {
            "sourcePrefix":"We have lamps that give the exact equivalent of ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Disponemos de lámparas que dan el equivalente exacto de ",
            "targetTerm":"luz solar",
            "targetSuffix":"."
         },
         {
            "sourcePrefix":"Plants need water and ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Las plantas necesitan agua y ",
            "targetTerm":"luz solar",
            "targetSuffix":"."
         },
         {
            "sourcePrefix":"So this requires ",
            "sourceTerm":"sunlight",
            "sourceSuffix":".",
            "targetPrefix":"Así que esto requiere ",
            "targetTerm":"luz solar",
            "targetSuffix":"."
         },
         {
            "sourcePrefix":"And this pocket of ",
            "sourceTerm":"sunlight",
            "sourceSuffix":" freed humans from their ...",
            "targetPrefix":"Y esta bolsa de ",
            "targetTerm":"luz solar",
            "targetSuffix":", liberó a los humanos de ..."
         },
         {
            "sourcePrefix":"Since there is no ",
            "sourceTerm":"sunlight",
            "sourceSuffix":", the air within ...",
            "targetPrefix":"Como no hay ",
            "targetTerm":"luz solar",
            "targetSuffix":", el aire atrapado en ..."
         },
         {
            "sourcePrefix":"The ",
            "sourceTerm":"sunlight",
            "sourceSuffix":" shining through the glass creates a ...",
            "targetPrefix":"La ",
            "targetTerm":"luz solar",
            "targetSuffix":" a través de la vidriera crea una ..."
         },
         {
            "sourcePrefix":"Less ice reflects less ",
            "sourceTerm":"sunlight",
            "sourceSuffix":", and more open ocean ...",
            "targetPrefix":"Menos hielo refleja menos ",
            "targetTerm":"luz solar",
            "targetSuffix":", y más mar abierto ..."
         },
         {
            "sourcePrefix":"",
            "sourceTerm":"Sunlight",
            "sourceSuffix":" is most intense at midday, so ...",
            "targetPrefix":"La ",
            "targetTerm":"luz solar",
            "targetSuffix":" es más intensa al mediodía, por lo que ..."
         },
         {
            "sourcePrefix":"... capture huge amounts of ",
            "sourceTerm":"sunlight",
            "sourceSuffix":", so fueling their growth.",
            "targetPrefix":"... capturan enormes cantidades de ",
            "targetTerm":"luz solar",
            "targetSuffix":" que favorecen su crecimiento."
         },
         {
            "sourcePrefix":"... full height, giving more direct ",
            "sourceTerm":"sunlight",
            "sourceSuffix":" in the winter.",
            "targetPrefix":"... altura completa, dando más ",
            "targetTerm":"luz solar",
            "targetSuffix":" directa durante el invierno."
         }
      ]
   }
]

Troubleshooting

Common HTTP status codes

HTTP status code Description Possible reason
200 OK The request was successful.
400 Bad Request A required parameter is missing, empty, or null. Or, the value passed to either a required or optional parameter is invalid. A common issue is a header that is too long.
401 Unauthorized The request isn't authorized. Check to make sure your key or token is valid and in the correct region. See also Authentication.
429 Too Many Requests You exceeded the quota or rate of requests allowed for your subscription.
502 Bad Gateway Network or server-side issue. May also indicate invalid headers.

Java users

If you're encountering connection issues, it may be that your TLS/SSL certificate is expired. To resolve this issue, install the DigiCertGlobalRootG2.crt to your private store.