Marcell Berta
Marcell Berta

Reputation: 1

Azure cognitive Service - Speech sample code failed with authentication error

The program returns: CANCELED: Reason=Error ErrorDetails=WebSocket Upgrade failed with an authentication error (401). Please check for correct subscription key (or authorization token) and region name. SessionId: cbfcdf7f26304343a08de6c398652053

I'm using my free trial subscription key and westus region. This is the sample code found here: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/quickstarts/speech-to-text-from-microphone?tabs=unity%2Cx-android%2Clinux%2Cjava-runtime&pivots=programming-language-csharp

using UnityEngine;
using UnityEngine.UI;
using Microsoft.CognitiveServices.Speech;
#if PLATFORM_ANDROID
using UnityEngine.Android;
#endif
#if PLATFORM_IOS
using UnityEngine.iOS;
using System.Collections;
#endif

public class Helloworld : MonoBehaviour
{
    // Hook up the two properties below with a Text and Button object in your UI.
    public Text outputText;
    public Button startRecoButton;

    private object threadLocker = new object();
    private bool waitingForReco;
    private string message;

    private bool micPermissionGranted = false;

#if PLATFORM_ANDROID || PLATFORM_IOS
    // Required to manifest microphone permission, cf.
    // https://docs.unity3d.com/Manual/android-manifest.html
    private Microphone mic;
#endif

    public async void ButtonClick()
    {
        // Creates an instance of a speech config with specified subscription key and service region.
        // Replace with your own subscription key and service region (e.g., "westus").
        var config = SpeechConfig.FromSubscription("yourSubscriptionKey", "yourRegion");

        // Make sure to dispose the recognizer after use!
        using (var recognizer = new SpeechRecognizer(config))
        {
            lock (threadLocker)
            {
                waitingForReco = true;
            }

            // Starts speech recognition, and returns after a single utterance is recognized. The end of a
            // single utterance is determined by listening for silence at the end or until a maximum of 15
            // seconds of audio is processed.  The task returns the recognition text as result.
            // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single
            // shot recognition like command or query.
            // For long-running multi-utterance recognition, use StartContinuousRecognitionAsync() instead.
            var result = await recognizer.RecognizeOnceAsync().ConfigureAwait(false);

            // Checks result.
            string newMessage = string.Empty;
            if (result.Reason == ResultReason.RecognizedSpeech)
            {
                newMessage = result.Text;
            }
            else if (result.Reason == ResultReason.NoMatch)
            {
                newMessage = "NOMATCH: Speech could not be recognized.";
            }
            else if (result.Reason == ResultReason.Canceled)
            {
                var cancellation = CancellationDetails.FromResult(result);
                newMessage = $"CANCELED: Reason={cancellation.Reason} ErrorDetails={cancellation.ErrorDetails}";
            }

            lock (threadLocker)
            {
                message = newMessage;
                waitingForReco = false;
            }
        }
    }

    void Start()
    {
        if (outputText == null)
        {
            UnityEngine.Debug.LogError("outputText property is null! Assign a UI Text element to it.");
        }
        else if (startRecoButton == null)
        {
            message = "startRecoButton property is null! Assign a UI Button to it.";
            UnityEngine.Debug.LogError(message);
        }
        else
        {
            // Continue with normal initialization, Text and Button objects are present.
#if PLATFORM_ANDROID
            // Request to use the microphone, cf.
            // https://docs.unity3d.com/Manual/android-RequestingPermissions.html
            message = "Waiting for mic permission";
            if (!Permission.HasUserAuthorizedPermission(Permission.Microphone))
            {
                Permission.RequestUserPermission(Permission.Microphone);
            }
#elif PLATFORM_IOS
            if (!Application.HasUserAuthorization(UserAuthorization.Microphone))
            {
                Application.RequestUserAuthorization(UserAuthorization.Microphone);
            }
#else
            micPermissionGranted = true;
            message = "Click button to recognize speech";
#endif
            startRecoButton.onClick.AddListener(ButtonClick);
        }
    }

    void Update()
    {
#if PLATFORM_ANDROID
        if (!micPermissionGranted && Permission.HasUserAuthorizedPermission(Permission.Microphone))
        {
            micPermissionGranted = true;
            message = "Click button to recognize speech";
        }
#elif PLATFORM_IOS
        if (!micPermissionGranted && Application.HasUserAuthorization(UserAuthorization.Microphone))
        {
            micPermissionGranted = true;
            message = "Click button to recognize speech";
        }
#endif

        lock (threadLocker)
        {
            if (startRecoButton != null)
            {
                startRecoButton.interactable = !waitingForReco && micPermissionGranted;
            }
            if (outputText != null)
            {
                outputText.text = message;
            }
        }
    }
}

Upvotes: 0

Views: 1396

Answers (1)

Rob Chambers
Rob Chambers

Reputation: 111

The sample code you pasted above still has the placeholder values for region and subscription key. Just double checking that you did in fact replace those strings with your own subscription key and region? If that's true, can you please turn on logging, run the code again, and then provide the log? We can help diagnose from there...

To turn on logging, see https://aka.ms/speech/logging.

Upvotes: 1

Related Questions