使用前提與環境準備：服務開通并購買
Step By Step
1.添加pom依賴
<dependency>
<groupId>com.alibaba.nls</groupId>
<artifactId>nls-sdk-tts</artifactId>
<version>2.2.1</version>
</dependency> 2.Code Sample
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.ByteBuffer;
import com.alibaba.nls.client.AccessToken;
import com.alibaba.nls.client.protocol.NlsClient;
import com.alibaba.nls.client.protocol.OutputFormatEnum;
import com.alibaba.nls.client.protocol.SampleRateEnum;
import com.alibaba.nls.client.protocol.tts.SpeechSynthesizer;
import com.alibaba.nls.client.protocol.tts.SpeechSynthesizerListener;
import com.alibaba.nls.client.protocol.tts.SpeechSynthesizerResponse;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* 此示例示範了：
* 語音合成API調用。
* 動态擷取token。
* 流式合成TTS。
* 首包延遲計算。
*/
// 語音合成Java SDK 調用示例
public class SpeechSynthesizerDemo {
private static final Logger logger = LoggerFactory.getLogger(SpeechSynthesizerDemo.class);
private static long startTime;
private String appKey;
NlsClient client;
public SpeechSynthesizerDemo(String appKey, String accessKeyId, String accessKeySecret) {
this.appKey = appKey;
//應用全局建立一個NlsClient執行個體，預設服務位址為阿裡雲線上服務位址。
//擷取token，使用時注意在accessToken.getExpireTime()過期前再次擷取。
AccessToken accessToken = new AccessToken(accessKeyId, accessKeySecret);
try {
accessToken.apply();
System.out.println("get token: " + accessToken.getToken() + ", expire time: " + accessToken.getExpireTime());
client = new NlsClient(accessToken.getToken());
} catch (IOException e) {
e.printStackTrace();
}
}
public SpeechSynthesizerDemo(String appKey, String accessKeyId, String accessKeySecret, String url) {
this.appKey = appKey;
AccessToken accessToken = new AccessToken(accessKeyId, accessKeySecret);
try {
accessToken.apply();
System.out.println("get token: " + accessToken.getToken() + ", expire time: " + accessToken.getExpireTime());
if(url.isEmpty()) {
client = new NlsClient(accessToken.getToken());
}else {
client = new NlsClient(url, accessToken.getToken());
}
} catch (IOException e) {
e.printStackTrace();
}
}
private static SpeechSynthesizerListener getSynthesizerListener() {
SpeechSynthesizerListener listener = null;
try {
listener = new SpeechSynthesizerListener() {
File f=new File("tts_test.wav");
FileOutputStream fout = new FileOutputStream(f);
private boolean firstRecvBinary = true;
//語音合成結束
@Override
public void onComplete(SpeechSynthesizerResponse response) {
//調用onComplete時表示所有TTS資料已接收完成，是以為整個合成資料的延遲。該延遲可能較大，不一定滿足實時場景。
System.out.println("name: " + response.getName() +
", status: " + response.getStatus()+
", output file :"+f.getAbsolutePath()
);
}
//語音合成的語音二進制資料
@Override
public void onMessage(ByteBuffer message) {
try {
if(firstRecvBinary) {
//計算首包語音流的延遲，收到第一包語音流時，即可以進行語音播放，以提升響應速度（特别是實時互動場景下）。
firstRecvBinary = false;
long now = System.currentTimeMillis();
logger.info("tts first latency : " + (now - SpeechSynthesizerDemo.startTime) + " ms");
}
byte[] bytesArray = new byte[message.remaining()];
message.get(bytesArray, 0, bytesArray.length);
fout.write(bytesArray);
} catch (IOException e) {
e.printStackTrace();
}
}
@Override
public void onFail(SpeechSynthesizerResponse response){
//task_id是調用方和服務端通信的唯一辨別，當遇到問題時需要提供task_id以便排查。
System.out.println(
"task_id: " + response.getTaskId() +
//狀态碼 20000000 表示識别成功
", status: " + response.getStatus() +
//錯誤資訊
", status_text: " + response.getStatusText());
}
};
} catch (Exception e) {
e.printStackTrace();
}
return listener;
}
public void process() {
SpeechSynthesizer synthesizer = null;
try {
//建立執行個體，建立連接配接。
synthesizer = new SpeechSynthesizer(client, getSynthesizerListener());
synthesizer.setAppKey(appKey);
//設定傳回音頻的編碼格式
synthesizer.setFormat(OutputFormatEnum.WAV);
//設定傳回音頻的采樣率
synthesizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_16K);
//發音人
synthesizer.setVoice("siyue");
//語調，範圍是-500~500，可選，預設是0。
synthesizer.setPitchRate(100);
//語速，範圍是-500~500，預設是0。
synthesizer.setSpeechRate(100);
//設定用于語音合成的文本
synthesizer.setText("歡迎使用阿裡巴巴智能語音合成服務，您可以說杭州明天天氣怎麼樣啊，如果天氣晴朗的話，我們大家準備去爬山野營，看看美麗的自然風景");
// 是否開啟字幕功能（傳回相應文本的時間戳），預設不開啟，需要注意并非所有發音人都支援該參數。
synthesizer.addCustomedParam("enable_subtitle", false);
//此方法将以上參數設定序列化為JSON格式發送給服務端，并等待服務端确認。
long start = System.currentTimeMillis();
synthesizer.start();
logger.info("tts start latency " + (System.currentTimeMillis() - start) + " ms");
SpeechSynthesizerDemo.startTime = System.currentTimeMillis();
//等待語音合成結束
synthesizer.waitForComplete();
logger.info("tts stop latency " + (System.currentTimeMillis() - start) + " ms");
} catch (Exception e) {
e.printStackTrace();
} finally {
//關閉連接配接
if (null != synthesizer) {
synthesizer.close();
}
}
}
public void shutdown() {
client.shutdown();
}
public static void main(String[] args) throws Exception {
String appKey = "XXXXXXXXXX";
String id = "XXXXXXXXXX";
String secret = "XXXXXXXXXX";
String url = ""; //預設值：wss://nls-gateway.cn-shanghai.aliyuncs.com/ws/v1
/* if (args.length == 3) {
appKey = args[0];
id = args[1];
secret = args[2];
} else if (args.length == 4) {
appKey = args[0];
id = args[1];
secret = args[2];
url = args[3];
} else {
System.err.println("run error, need params(url is optional): " + "<app-key> <AccessKeyId> <AccessKeySecret> [url]");
System.exit(-1);
}*/
SpeechSynthesizerDemo demo = new SpeechSynthesizerDemo(appKey, id, secret, url);
demo.process();
demo.shutdown();
}
} 3.測試結果
get token: b42af56233c84ca5a6362e6f24cfbc2e, expire time: 1640198528
name: SynthesisCompleted, status: 20000000, output file :D:\ZhinyYjh\tts_test.wav
更多參考
快速開始智能語言互動：
語音合成![Java小案例——随機數猜測随機數猜測[圖]](data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACwAAAAAAQABAAACAkQBADs=)