import com.alibaba.dashscope.audio.qwen_tts_realtime.*;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.google.gson.JsonObject;
import javax.sound.sampled.LineUnavailableException;
import javax.sound.sampled.SourceDataLine;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.AudioSystem;
import java.io.*;
import java.util.Base64;
import java.util.Queue;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.atomic.AtomicReference;
import java.util.concurrent.ConcurrentLinkedQueue;
import java.util.concurrent.atomic.AtomicBoolean;
public class Main {
static String[] textToSynthesize = {
"对吧~我就特别喜欢这种超市",
"尤其是过年的时候",
"去逛超市",
"就会觉得",
"超级超级开心！",
"想买好多好多的东西呢！"
};
public static QwenTtsRealtimeAudioFormat ttsFormat = QwenTtsRealtimeAudioFormat.PCM_24000HZ_MONO_16BIT;
// 实时PCM音频播放器类
public static class RealtimePcmPlayer {
private int sampleRate;
private SourceDataLine line;
private AudioFormat audioFormat;
private Thread decoderThread;
private Thread playerThread;
private AtomicBoolean stopped = new AtomicBoolean(false);
private Queue<String> b64AudioBuffer = new ConcurrentLinkedQueue<>();
private Queue<byte[]> RawAudioBuffer = new ConcurrentLinkedQueue<>();
private ByteArrayOutputStream totalAudioStream = new ByteArrayOutputStream();
// 构造函数初始化音频格式和音频线路
public RealtimePcmPlayer(int sampleRate) throws LineUnavailableException {
this.sampleRate = sampleRate;
this.audioFormat = new AudioFormat(this.sampleRate, 16, 1, true, false);
DataLine.Info info = new DataLine.Info(SourceDataLine.class, audioFormat);
line = (SourceDataLine) AudioSystem.getLine(info);
line.open(audioFormat);
line.start();
decoderThread = new Thread(new Runnable() {
@Override
public void run() {
while (!stopped.get()) {
String b64Audio = b64AudioBuffer.poll();
if (b64Audio != null) {
byte[] rawAudio = Base64.getDecoder().decode(b64Audio);
RawAudioBuffer.add(rawAudio);
// 将音频数据写入 totalAudioStream
try {
totalAudioStream.write(rawAudio);
} catch (IOException e) {
throw new RuntimeException(e);
}
} else {
try {
Thread.sleep(100);
} catch (InterruptedException e) {
throw new RuntimeException(e);
}
}
}
}
});
playerThread = new Thread(new Runnable() {
@Override
public void run() {
while (!stopped.get()) {
byte[] rawAudio = RawAudioBuffer.poll();
if (rawAudio != null) {
try {
playChunk(rawAudio);
} catch (IOException e) {
throw new RuntimeException(e);
} catch (InterruptedException e) {
throw new RuntimeException(e);
}
} else {
try {
Thread.sleep(100);
} catch (InterruptedException e) {
throw new RuntimeException(e);
}
}
}
}
});
decoderThread.start();
playerThread.start();
}
// 播放一个音频块并阻塞直到播放完成
private void playChunk(byte[] chunk) throws IOException, InterruptedException {
if (chunk == null || chunk.length == 0) return;
int bytesWritten = 0;
while (bytesWritten < chunk.length) {
bytesWritten += line.write(chunk, bytesWritten, chunk.length - bytesWritten);
}
int audioLength = chunk.length / (this.sampleRate*2/1000);
// 等待缓冲区中的音频播放完成
Thread.sleep(audioLength - 10);
}
public void write(String b64Audio) {
b64AudioBuffer.add(b64Audio);
}
public void cancel() {
b64AudioBuffer.clear();
RawAudioBuffer.clear();
}
public void waitForComplete() throws InterruptedException {
while (!b64AudioBuffer.isEmpty() || !RawAudioBuffer.isEmpty()) {
Thread.sleep(100);
}
line.drain();
}
public void shutdown() throws InterruptedException, IOException {
stopped.set(true);
decoderThread.join();
playerThread.join();
// 保存完整音频文件
File file = new File("TotalAudio_"+ttsFormat.getSampleRate()+"."+ttsFormat.getFormat());
try (FileOutputStream fos = new FileOutputStream(file)) {
fos.write(totalAudioStream.toByteArray());
}
if (line != null && line.isRunning()) {
line.drain();
line.close();
}
}
}
public static void main(String[] args) throws InterruptedException, LineUnavailableException, IOException {
QwenTtsRealtimeParam param = QwenTtsRealtimeParam.builder()
// 如需使用指令控制功能，请将model替换为qwen3-tts-instruct-flash-realtime
.model("qwen3-tts-flash-realtime")
// 以下为华北2（北京）地域的配置。
.url("wss://dashscope.aliyuncs.com/api-ws/v1/realtime")
// 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
.apikey(System.getenv("DASHSCOPE_API_KEY"))
.build();
AtomicReference<CountDownLatch> completeLatch = new AtomicReference<>(new CountDownLatch(1));
final AtomicReference<QwenTtsRealtime> qwenTtsRef = new AtomicReference<>(null);
// 创建实时音频播放器实例
RealtimePcmPlayer audioPlayer = new RealtimePcmPlayer(24000);
QwenTtsRealtime qwenTtsRealtime = new QwenTtsRealtime(param, new QwenTtsRealtimeCallback() {
@Override
public void onOpen() {
// 连接建立时的处理
}
@Override
public void onEvent(JsonObject message) {
String type = message.get("type").getAsString();
switch(type) {
case "session.created":
// 会话创建时的处理
if (message.has("session")) {
String eventId = message.get("event_id").getAsString();
String sessionId = message.get("session").getAsJsonObject().get("id").getAsString();
System.out.println("[onEvent] session.created, session_id: "
+ sessionId + ", event_id: " + eventId);
}
break;
case "response.audio.delta":
String recvAudioB64 = message.get("delta").getAsString();
// 实时播放音频
audioPlayer.write(recvAudioB64);
break;
case "response.done":
// 响应完成时的处理
break;
case "session.finished":
// 会话结束时的处理
completeLatch.get().countDown();
default:
break;
}
}
@Override
public void onClose(int code, String reason) {
// 连接关闭时的处理
}
});
qwenTtsRef.set(qwenTtsRealtime);
try {
qwenTtsRealtime.connect();
} catch (NoApiKeyException e) {
throw new RuntimeException(e);
}
QwenTtsRealtimeConfig config = QwenTtsRealtimeConfig.builder()
.voice("Cherry")
.responseFormat(ttsFormat)
.mode("server_commit")
// 如需使用指令控制功能，请取消下方注释，并将model替换为qwen3-tts-instruct-flash-realtime
// .instructions("")
// .optimizeInstructions(true)
.build();
qwenTtsRealtime.updateSession(config);
for (String text:textToSynthesize) {
qwenTtsRealtime.appendText(text);
Thread.sleep(100);
}
qwenTtsRealtime.finish();
completeLatch.get().await();
qwenTtsRealtime.close();
// 等待音频播放完成并关闭播放器
audioPlayer.waitForComplete();
audioPlayer.shutdown();
System.exit(0);
}
}