リアルタイム音声合成

import com.alibaba.dashscope.audio.tts.SpeechSynthesisResult;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisAudioFormat;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
import com.alibaba.dashscope.common.ResultCallback;
import com.alibaba.dashscope.utils.Constants;
import java.io.FileOutputStream;
import java.nio.ByteBuffer;

public class Main {
    public static void main(String[] args) throws Exception {
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference";
        try (FileOutputStream audio = new FileOutputStream("output.mp3")) {
            SpeechSynthesisParam param = SpeechSynthesisParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-audio-3.1-tts-flash")
                .voice("longanhuan_v3.1")
                .format(SpeechSynthesisAudioFormat.MP3_24000HZ_MONO_256KBPS)
                .build();
            ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<>() {
                @Override
                public void onEvent(SpeechSynthesisResult result) {
                    ByteBuffer buffer = result.getAudioFrame();
                    if (buffer != null) {
                        byte[] bytes = new byte[buffer.remaining()];
                        buffer.get(bytes);
                        try { audio.write(bytes); }
                        catch (Exception e) { throw new RuntimeException(e); }
                    }
                }
                @Override
                public void onComplete() {}
                public void onError(Exception e) { e.printStackTrace(); }
            };
            SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
            try {
                for (String text : new String[]{"Hello, welcome to Alibaba Cloud Model Studio.", "Text can be sent in segments, and audio is returned progressively."}) {
                    synthesizer.streamingCall(text);
                }
                synthesizer.streamingComplete(60000);
            } finally {
                synthesizer.getDuplexApi().close(1000, "done");
            }
        }
    }
}