Real-time speech synthesis

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.Scanner;
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 {
    public static QwenTtsRealtimeAudioFormat ttsFormat = QwenTtsRealtimeAudioFormat.PCM_24000HZ_MONO_16BIT;
    // Real-time PCM audio player
    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();

        // Initialize the audio format and audio line.
        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);
                            // Write audio data to 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();
        }

        // Play an audio chunk and block until playback completes.
        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);
            // Wait for the buffered audio to finish playing.
            Thread.sleep(audioLength - 10);
        }

        public void write(String b64Audio) {
            b64AudioBuffer.add(b64Audio);
        }

        public void cancel() {
            b64AudioBuffer.clear();
            RawAudioBuffer.clear();
        }

        public void waitForComplete() throws InterruptedException {
            // Wait for all buffered audio data to finish playing.
            while (!b64AudioBuffer.isEmpty() || !RawAudioBuffer.isEmpty()) {
                Thread.sleep(100);
            }
            // Wait for the audio line to drain.
            line.drain();
        }

        public void shutdown() throws InterruptedException {
            stopped.set(true);
            decoderThread.join();
            playerThread.join();
            // Save the complete audio file.
            File file = new File("TotalAudio_"+ttsFormat.getSampleRate()+"."+ttsFormat.getFormat());
            try (FileOutputStream fos = new FileOutputStream(file)) {
                fos.write(totalAudioStream.toByteArray());
            } catch (FileNotFoundException e) {
                throw new RuntimeException(e);
            } catch (IOException e) {
                throw new RuntimeException(e);
            }
            if (line != null && line.isRunning()) {
                line.drain();
                line.close();
            }
        }
    }

    public static void main(String[] args) throws InterruptedException, LineUnavailableException, FileNotFoundException {
        Scanner scanner = new Scanner(System.in);

        QwenTtsRealtimeParam param = QwenTtsRealtimeParam.builder()
                // To use instruction control, replace the model with qwen3-tts-instruct-flash-realtime.
                .model("qwen3-tts-flash-realtime")
                // China (Beijing) region
                .url("wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime")
                // API keys differ between Singapore and China (Beijing). See https://www.alibabacloud.com/help/en/model-studio/get-api-key.
                .apikey(System.getenv("DASHSCOPE_API_KEY"))
                .build();

        AtomicReference<CountDownLatch> completeLatch = new AtomicReference<>(new CountDownLatch(1));

        // Create a real-time player instance.
        RealtimePcmPlayer audioPlayer = new RealtimePcmPlayer(24000);

        final AtomicReference<QwenTtsRealtime> qwenTtsRef = new AtomicReference<>(null);
        QwenTtsRealtime qwenTtsRealtime = new QwenTtsRealtime(param, new QwenTtsRealtimeCallback() {
            @Override
            public void onOpen() {
                System.out.println("connection opened");
                System.out.println("Enter text and press Enter to send. Enter 'quit' to exit the program.");
            }
            @Override
            public void onEvent(JsonObject message) {
                String type = message.get("type").getAsString();
                switch(type) {
                    case "session.created":
                        System.out.println("start session: " + message.get("session").getAsJsonObject().get("id").getAsString());
                        break;
                    case "response.audio.delta":
                        String recvAudioB64 = message.get("delta").getAsString();
                        byte[] rawAudio = Base64.getDecoder().decode(recvAudioB64);
                        // Play audio in real time.
                        audioPlayer.write(recvAudioB64);
                        break;
                    case "response.done":
                        System.out.println("response done");
                        // Wait for audio playback to complete.
                        try {
                            audioPlayer.waitForComplete();
                        } catch (InterruptedException e) {
                            throw new RuntimeException(e);
                        }
                        // Prepare for the next input.
                        completeLatch.get().countDown();
                        break;
                    case "session.finished":
                        System.out.println("session finished");
                        if (qwenTtsRef.get() != null) {
                            System.out.println("[Metric] response: " + qwenTtsRef.get().getResponseId() +
                                    ", first audio delay: " + qwenTtsRef.get().getFirstAudioDelay() + " ms");
                        }
                        completeLatch.get().countDown();
                    default:
                        break;
                }
            }
            @Override
            public void onClose(int code, String reason) {
                System.out.println("connection closed code: " + code + ", reason: " + reason);
                try {
                    // Wait for playback to complete, then shut down the player.
                    audioPlayer.waitForComplete();
                    audioPlayer.shutdown();
                } catch (InterruptedException e) {
                    throw new RuntimeException(e);
                }
            }
        });
        qwenTtsRef.set(qwenTtsRealtime);
        try {
            qwenTtsRealtime.connect();
        } catch (NoApiKeyException e) {
            throw new RuntimeException(e);
        }
        QwenTtsRealtimeConfig config = QwenTtsRealtimeConfig.builder()
                .voice("Cherry")
                .responseFormat(ttsFormat)
                .mode("commit")
                // To use instruction control, uncomment the following lines and replace the model with qwen3-tts-instruct-flash-realtime.
                // .instructions("")
                // .optimizeInstructions(true)
                .build();
        qwenTtsRealtime.updateSession(config);

        // Read user input in a loop.
        while (true) {
            System.out.print("Enter the text to synthesize: ");
            String text = scanner.nextLine();

            // Exit when the user enters 'quit'.
            if ("quit".equalsIgnoreCase(text.trim())) {
                System.out.println("Closing the connection...");
                qwenTtsRealtime.finish();
                completeLatch.get().await();
                break;
            }

            // Skip empty input.
            if (text.trim().isEmpty()) {
                continue;
            }

            // Re-initialize the countdown latch.
            completeLatch.set(new CountDownLatch(1));

            // Send the text.
            qwenTtsRealtime.appendText(text);
            qwenTtsRealtime.commit();

            // Wait for the current synthesis to complete.
            completeLatch.get().await();
        }

        // Clean up resources.
        audioPlayer.waitForComplete();
        audioPlayer.shutdown();
        scanner.close();
        System.exit(0);
    }
}