Use the Translator API to detect Language

Spread the love
In this tutorial we are going to see how to use the Translator Text API to detect Language from Text.


  1. To run the sample code you must have an edition of  Visual Studio installed.
  2. You will need the Json.NET NuGet package.
  3. You will need the .NET SDK installed in your machine
  4. You will need an Azure Cognitive Services account with a Translator Text resource. If you don’t have an account, you can use the free trial to get a subscription key.

Create your Project

To create an application to translate your text follow the steps below:

  1. Create a .NET Core Console Application in Visual Studio 2017
  2. Add the nuget package
    Install-Package Newtonsoft.Json
  3. Add the following code under Program
    static void Identify()
                string host = "";
                string route = "/detect?api-version=3.0";
                string subscriptionKey = "enter your subscription key";
                System.Object[] body = new System.Object[] { new { Text = @"Ola, tudo bem?" } };
                var requestBody = JsonConvert.SerializeObject(body);
                using (var client = new HttpClient())
                using (var request = new HttpRequestMessage())
                    request.Method = HttpMethod.Post;
                    request.RequestUri = new Uri(host + route);
                    request.Content = new StringContent(requestBody, Encoding.UTF8, "application/json");
                    request.Headers.Add("Ocp-Apim-Subscription-Key", subscriptionKey);
                    var response = client.SendAsync(request).Result;
                    var jsonResponse = response.Content.ReadAsStringAsync().Result;
                    Console.WriteLine("Press any key to continue.");
            static void Main(string[] args)
  4. Replace your subscription key here: string subscriptionKey = “enter your subscription key”;
  5. Add here the text you want to be translated System.Object[] body = new System.Object[] { new { Text = @”Ola, tudo bem?” } }; Document size must be under 5,000 characters per document, and you can have up to 1,000 items (IDs) per collection.
  6. Run the Program

Get Results

The result is in the following format. That’s it, we have identified the correct Language (Portuguese)! A positive score of 1.0 expresses the highest possible confidence level of the analysis

    "documents": [
            "id": "1",
            "detectedLanguages": [
                    "name": "Portuguese",
                    "iso6391Name": "pt",
                    "score": 1

You can find the complete source code in my Github in this repository in the LanguageIdentify Project.


Leave a Reply

Your email address will not be published. Required fields are marked *