Unity接微软认知服务语音合成（Azure-TTS）

上一篇我介绍了如何接入微软认知服务的语音识别，这篇文章我将为大家介绍如何接入微软认知服务的语音合成（以下简称语音合成）。语音合成中也需要用到YourSubscriptionKey和YourServiceRegion，获取方式同语音识别，这两个**与语音识别是通用的，所用到的SDK与语音识别的也是一样。首先我们还是要新建一个场景，如下图所示

然后新建脚本，命名为MicroSoftTTSDemo，然后编辑脚本，将以下内容粘贴到脚本中

using UnityEngine;
using UnityEngine.UI;
using Microsoft.CognitiveServices.Speech;
using System;
using System.IO;
using System.Collections;
using Microsoft.CognitiveServices.Speech.Audio;
using System.Threading.Tasks;
using UnityEngine.Networking;

public class MicroSoftTTSDemo : MonoBehaviour
{
    // Hook up the three properties below with a Text, InputField and Button object in your UI.
    public Text outputText;
    public InputField inputField;
    public Button speakButton;
    public AudioSource audioSource;

    private object threadLocker = new object();
    private bool waitingForSpeak;
    private string message;
    public string path;
    public string fileName;
    public string audioType;
    public DateTime startTime;
    public DateTime endTime;
    public Text timeText;
    void Start()
    {
        if (outputText == null)
        {
            UnityEngine.Debug.LogError("outputText property is null! Assign a UI Text element to it.");
        }
        else if (inputField == null)
        {
            message = "inputField property is null! Assign a UI InputField element to it.";
            UnityEngine.Debug.LogError(message);
        }
        else if (speakButton == null)
        {
            message = "speakButton property is null! Assign a UI Button to it.";
            UnityEngine.Debug.LogError(message);
        }
        else
        {
            // Continue with normal initialization, Text, InputField and Button objects are present.
            //inputField.text = "Enter text you wish spoken here.";
            //message = "Click button to synthesize speech";
            speakButton.onClick.AddListener(ButtonClick);
        }
    }

    void Update()
    {
        lock (threadLocker)
        {
            if (speakButton != null)
            {
                speakButton.interactable = !waitingForSpeak;
            }

            if (outputText != null)
            {
                outputText.text = message;
            }
        }
    }

    public void ButtonClick()
    {
        startTime = DateTime.Now;
        // 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", "YourServiceRegion");
        // Creates a speech synthesizer.
        // Make sure to dispose the synthesizer after use!
        using (var synthsizer = new SpeechSynthesizer(config, null))
        {
            lock (threadLocker)
            {
                waitingForSpeak = true;
            }
            // Starts speech synthesis, and returns after a single utterance is synthesized.
            var result = synthsizer.SpeakTextAsync(inputField.text).Result;
            //print("after   " + DateTime.Now);

            // Checks result.
            string newMessage = string.Empty;

            if (result.Reason == ResultReason.SynthesizingAudioCompleted)
            {
                // Since native playback is not yet supported on Unity yet (currently only supported on Windows/Linux Desktop),
                // use the Unity API to play audio here as a short term solution.
                // Native playback support will be added in the future release.
                var sampleCount = result.AudioData.Length / 2;
                var audioData = new float[sampleCount];
                for (var i = 0; i < sampleCount; ++i)
                {
                    audioData[i] = (short)(result.AudioData[i * 2 + 1] << 8 | result.AudioData[i * 2]) / 32768.0F;

                }
                // The default output audio format is 16K 16bit mono
                var audioClip = AudioClip.Create("SynthesizedAudio", sampleCount, 1, 16000, false);
                audioClip.SetData(audioData, 0);
                audioSource.clip = audioClip;
                audioSource.Play();
                endTime = DateTime.Now;
                timeText.text = "合成前时间：" + startTime + "     合成成功时间：" + endTime;

                newMessage = "Speech synthesis succeeded!";
            }

            else if (result.Reason == ResultReason.Canceled)
            {
                var cancellation = SpeechSynthesisCancellationDetails.FromResult(result);
                newMessage = $"CANCELED:\nReason=[{cancellation.Reason}]\nErrorDetails=[{cancellation.ErrorDetails}]\nDid you update the subscription info?";
            }

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

保存脚本后点击运行，在InputFeild中输入英文文本，然后点击Button，即可播放你输入的英文。至此语音合成就已经完成。微软语音合成的发音与真人发音一模一样，不会有机械化的感觉。

下篇文章将为大家介绍微软语音SDK接好后打包所遇到的坑