Qwen-Audio-TTS Java SDK

import com.alibaba.dashscope.audio.tts.SpeechSynthesisResult;
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.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.concurrent.CountDownLatch;

class TimeUtils {
    private static final DateTimeFormatter formatter =
            DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss.SSS");

    public static String getTimestamp() {
        return LocalDateTime.now().format(formatter);
    }
}

public class Main {
    // Model
    private static String model = "qwen-audio-3.0-tts-flash";
    // Voice
    private static String voice = "longanhuan_v3.6";

    public static void streamAudioDataToSpeaker() {
        CountDownLatch latch = new CountDownLatch(1);

        // Implementasikan antarmuka ResultCallback
        ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                if (result.getAudioFrame() != null) {
                    // Implementasikan logika untuk menyimpan data audio secara lokal di sini
                    System.out.println(TimeUtils.getTimestamp() + " Audio received");
                }
                // Dapatkan informasi output, termasuk tipe event dan teks asli
                if (result.getOutput() != null && result.getOutput().has("type")) {
                    System.out.println("Event type: " + result.getOutput().get("type").getAsString()
                            + ", Original text: " + (result.getOutput().has("original_text") ? result.getOutput().get("original_text").getAsString() : ""));
                }
            }

            @Override
            public void onComplete() {
                System.out.println(TimeUtils.getTimestamp() + " Complete received, speech synthesis finished");
                latch.countDown();
            }

            @Override
            public void onError(Exception e) {
                System.out.println("Exception occurred: " + e.toString());
                latch.countDown();
            }
        };

        // Parameter permintaan
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // Kunci API untuk wilayah Singapura dan Beijing berbeda. Dapatkan Kunci API: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Studio Model Anda: .apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();
        // Memberikan "callback" sebagai parameter kedua mengaktifkan mode asinkron
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // Panggilan non-blocking yang langsung mengembalikan null (hasil aktual dikirimkan secara asinkron melalui antarmuka callback). Audio biner diterima secara real time melalui metode onEvent antarmuka callback
        try {
            synthesizer.call("What's the weather like today?");
            // Tunggu hingga sintesis selesai
            latch.await();
            // Tunggu hingga thread pemutaran selesai memutar
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Tutup koneksi WebSocket setelah tugas selesai
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        // Transmisi teks pertama memerlukan pembentukan koneksi WebSocket, sehingga latensi paket pertama mencakup waktu pembentukan koneksi
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) {
        // Konfigurasi berikut untuk wilayah Singapura. Ganti "{WorkspaceId}" dengan workspace ID Anda yang sebenarnya. Konfigurasi berbeda untuk setiap wilayah.
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}

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.time.LocalDateTime;
import java.time.format.DateTimeFormatter;

class TimeUtils {
    private static final DateTimeFormatter formatter =
            DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss.SSS");

    public static String getTimestamp() {
        return LocalDateTime.now().format(formatter);
    }
}

public class Main {
    private static String[] textArray = {"Streaming text-to-speech SDK, ",
            "can convert input text ", "into audio binary data. ", "Compared to non-streaming speech synthesis, ",
            "streaming synthesis offers better real-time performance. ", "While users input text, ",
            "they can hear nearly synchronous audio output, ", "greatly enhancing the interactive experience ",
            "and reducing user wait time. ", "It is suitable for calling large-scale ", "language models (LLMs) to ",
            "perform speech synthesis ", "with streaming text input."};
    private static String model = "qwen-audio-3.0-tts-flash"; // Model
    private static String voice = "longanhuan_v3.6"; // Voice

    public static void streamAudioDataToSpeaker() {
        // Konfigurasikan fungsi callback
        ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                // System.out.println("Message received: " + result);
                if (result.getAudioFrame() != null) {
                    // Implementasikan logika untuk memproses data audio di sini
                    System.out.println(TimeUtils.getTimestamp() + " Audio received");
                }
            }

            @Override
            public void onComplete() {
                System.out.println(TimeUtils.getTimestamp() + " Complete received, speech synthesis finished");
            }

            @Override
            public void onError(Exception e) {
                System.out.println("Exception occurred: " + e.toString());
            }
        };

        // Parameter permintaan
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // Kunci API untuk wilayah Singapura dan Beijing berbeda. Dapatkan Kunci API: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Studio Model Anda: .apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model(model)
                        .voice(voice)
                        .format(SpeechSynthesisAudioFormat
                                .PCM_22050HZ_MONO_16BIT) // Gunakan PCM atau MP3 untuk sintesis streaming
                        .build();
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // Metode call dengan Callback tidak akan memblokir thread saat ini
        try {
            for (String text : textArray) {
                // Kirim fragmen teks dan terima audio biner secara real time melalui metode onEvent antarmuka callback
                synthesizer.streamingCall(text);
            }
            // Tunggu hingga sintesis suara streaming selesai
            synthesizer.streamingComplete();
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Tutup koneksi WebSocket setelah tugas selesai
            synthesizer.getDuplexApi().close(1000, "bye");
        }

        // Transmisi teks pertama memerlukan pembentukan koneksi WebSocket, sehingga latensi paket pertama mencakup waktu pembentukan koneksi
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) {
        // Konfigurasi berikut untuk wilayah Singapura. Ganti "{WorkspaceId}" dengan workspace ID Anda yang sebenarnya. Konfigurasi berbeda untuk setiap wilayah.
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}

import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
import io.reactivex.BackpressureStrategy;
import io.reactivex.Flowable;

import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;

class TimeUtils {
    private static final DateTimeFormatter formatter =
            DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss.SSS");

    public static String getTimestamp() {
        return LocalDateTime.now().format(formatter);
    }
}

public class Main {
    private static String[] textArray = {"Streaming text-to-speech SDK, ",
            "can convert input text ", "into audio binary data. ", "Compared to non-streaming speech synthesis, ",
            "streaming synthesis offers better real-time performance. ", "While users input text, ",
            "they can hear nearly synchronous audio output, ", "greatly enhancing the interactive experience ",
            "and reducing user wait time. ", "It is suitable for calling large-scale ", "language models (LLMs) to ",
            "perform speech synthesis ", "with streaming text input."};
    private static String model = "qwen-audio-3.0-tts-flash";
    private static String voice = "longanhuan_v3.6";

    public static void streamAudioDataToSpeaker() throws NoApiKeyException {
        // Simulasikan input streaming
        Flowable<String> textSource = Flowable.create(emitter -> {
            new Thread(() -> {
                for (int i = 0; i < textArray.length; i++) {
                    emitter.onNext(textArray[i]);
                    try {
                        Thread.sleep(1000);
                    } catch (InterruptedException e) {
                        throw new RuntimeException(e);
                    }
                }
                emitter.onComplete();
            }).start();
        }, BackpressureStrategy.BUFFER);

        // Parameter permintaan
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // Kunci API untuk wilayah Singapura dan Beijing berbeda. Dapatkan Kunci API: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // Jika variabel lingkungan belum dikonfigurasi, ganti baris berikut dengan Kunci API Studio Model Anda: .apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
        synthesizer.streamingCallAsFlowable(textSource).blockingForEach(result -> {
            if (result.getAudioFrame() != null) {
                // Implementasikan logika untuk memutar audio di sini
                System.out.println(
                        TimeUtils.getTimestamp() +
                                " Binary audio size: " + result.getAudioFrame().capacity());
            }
            // Dapatkan informasi output, termasuk tipe event dan teks asli
            if (result.getOutput() != null && result.getOutput().has("type")) {
                System.out.println("Event type: " + result.getOutput().get("type").getAsString()
                        + ", Original text: " + (result.getOutput().has("original_text") ? result.getOutput().get("original_text").getAsString() : ""));
            }
        });
        synthesizer.getDuplexApi().close(1000, "bye");
        // Transmisi teks pertama memerlukan pembentukan koneksi WebSocket, sehingga latensi paket pertama mencakup waktu pembentukan koneksi
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) throws NoApiKeyException {
        // Konfigurasi berikut untuk wilayah Singapura. Ganti "{WorkspaceId}" dengan workspace ID Anda yang sebenarnya. Konfigurasi berbeda untuk setiap wilayah.
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}