Azure的tts文本转语音服务使用

最新推荐文章于 2025-04-12 10:22:35 发布

爱飞的男孩

最新推荐文章于 2025-04-12 10:22:35 发布

阅读量1.7k

点赞数 2

文章标签： azure microsoft java

本文链接：https://blog.csdn.net/qq_54230484/article/details/131597829

版权

该代码示例演示了如何使用Java和MicrosoftAzureCognitiveServices的语音服务将文本转换为音频文件（wav格式）。程序配置了特定的语音样式和停顿，输入文本后生成对应的音频并保存到指定路径。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

使用文件接收音频文件即可跳过播报过程：

package com.tts;

import com.microsoft.cognitiveservices.speech.*;
import com.microsoft.cognitiveservices.speech.audio.AudioConfig;

import java.io.*;
import java.util.Arrays;
import java.util.Scanner;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;

/**
 * 文本转语音
 * @author dftdla
 */
public class SpeechSynthesis {

    private static final String speechKey;
    private static final String speechRegion;
    //情绪度
    private static final String styleDegree = "1.4";
    //情绪
    private static final String style = "excited";
    //停顿点持续时间
    private static final String commasilenceExact = "600ms";
    //设置超时时间为5s
    private static final long timeout = 5;
    private static final TimeUnit unit = TimeUnit.SECONDS;

    public static void main(String[] args) throws InterruptedException, ExecutionException, IOException {

        //替换成自己的key和regin
        SpeechConfig speechConfig = SpeechConfig.fromSubscription(speechKey, speechRegion);

        //azure中菲律宾的女音 ： fil-PH-BlessicaNeural
        speechConfig.setSpeechSynthesisVoiceName("en-IE-EmilyNeural");

        SpeechSynthesizer speechSynthesizer;
        String text;
        Scanner scanner = new Scanner(System.in);
        text = scanner.next();

        speechConfig.setSpeechSynthesisOutputFormat(SpeechSynthesisOutputFormat.Riff24Khz16BitMonoPcm);

        File file = new File("E:\\home\\admin\\source\\upload\\audio\\00a4da29-eec2-4464-8315-d9d7789f7240.wav");
        file.getParentFile().mkdirs();

        AudioConfig audioConfig = AudioConfig.fromWavFileOutput(file.getAbsolutePath());

        try {
            speechSynthesizer = new SpeechSynthesizer(speechConfig, audioConfig);

            SpeechSynthesisResult result = speechSynthesizer.SpeakText(text);

            speechSynthesizer.StartSpeakingText(Arrays.toString(result.getAudioData()));
//            speechSynthesizer.waitUntilDone();
            speechSynthesizer.StopSpeakingAsync();
        } catch(Exception ex) {
            System.out.println(ex.getMessage()+"??");
        } finally {
            System.out.println("done");
        }
        System.exit(0);
    }
}