Alibaba Cloud Model Studio：SDK Java sintesis ucapan CosyVoice

import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.ByteBuffer;

public class Main {
    // Model
    private static String model = "cosyvoice-v3-flash";
    // Voice
    private static String voice = "longanyang";

    public static void streamAudioDataToSpeaker() {
        // Parameter permintaan
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // Jika Kunci API belum dikonfigurasi sebagai variabel lingkungan, hapus komentar baris berikut dan ganti your-api-key dengan Kunci API Anda.
                        // .apiKey("your-api-key")
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();

        // Mode sinkron: Nonaktifkan callback (parameter kedua bernilai null).
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
        ByteBuffer audio = null;
        try {
            // Blokir hingga audio dikembalikan.
            audio = synthesizer.call("What's the weather like today?");
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Tutup koneksi WebSocket setelah tugas selesai.
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        if (audio != null) {
            // Simpan data audio ke file lokal bernama "output.mp3".
            File file = new File("output.mp3");
            // Koneksi WebSocket harus dibuat saat teks dikirim pertama kali. Oleh karena itu, latensi paket pertama mencakup waktu pembuatan koneksi.
            System.out.println(
                    "[Metric] Request ID: "
                            + synthesizer.getLastRequestId()
                            + ", First-packet latency (ms): "
                            + synthesizer.getFirstPackageDelay());
            try (FileOutputStream fos = new FileOutputStream(file)) {
                fos.write(audio.array());
            } catch (IOException e) {
                throw new RuntimeException(e);
            }
        }
    }

    public static void main(String[] args) {
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}

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 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 = "cosyvoice-v3-flash";
    // Voice
    private static String voice = "longanyang";

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

        // Implementasikan antarmuka ResultCallback.
        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 menyimpan data audio ke file lokal di sini.
                    System.out.println(TimeUtils.getTimestamp() + " Audio received");
                }
            }

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

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

        // Parameter permintaan
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // Jika Anda belum mengonfigurasi Kunci API sebagai variabel lingkungan, hapus komentar baris berikut dan ganti "your-api-key" dengan Kunci API Anda.
                        // .apiKey("your-api-key")
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();
        // Kirimkan callback sebagai parameter kedua untuk mengaktifkan mode asinkron.
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // Ini adalah panggilan non-blocking yang langsung mengembalikan null. Hasil aktual dikirimkan secara asinkron melalui antarmuka callback. Ambil data audio biner secara real-time di metode onEvent antarmuka callback.
        try {
            synthesizer.call("What's the weather like today?");
            // Tunggu hingga sintesis selesai.
            latch.await();
            // Tunggu hingga semua thread pemutaran selesai.
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Tutup koneksi WebSocket setelah tugas selesai.
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        // Koneksi WebSocket harus dibuat saat teks dikirim pertama kali. Oleh karena itu, latensi paket pertama mencakup waktu pembuatan koneksi.
        System.out.println(
                "[Metric] Request ID: "
                        + synthesizer.getLastRequestId()
                        + ", First-packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) {
        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 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 {
    private static String[] textArray = {"The streaming text-to-speech SDK, ",
            "can convert input text ", "into binary audio data. ", "Compared to non-streaming speech synthesis, ",
            "streaming synthesis offers the advantage of stronger ", "real-time performance. Users can hear ",
            "nearly synchronous speech output while inputting text, ", "greatly enhancing the interactive experience ",
            "and reducing user waiting time. ", "It is suitable for scenarios that call large ", "language models (LLMs) to perform ",
            "speech synthesis by ", "streaming text input."};
    private static String model = "cosyvoice-v3-flash"; // Model
    private static String voice = "longanyang"; // 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 is finished.");
            }

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

        // Parameter permintaan
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // Jika Kunci API belum diatur sebagai variabel lingkungan, hapus komentar baris berikut dan ganti your-api-key dengan kunci Anda.
                        // .apiKey("your-api-key")
                        .model(model)
                        .voice(voice)
                        .format(SpeechSynthesisAudioFormat
                                .PCM_22050HZ_MONO_16BIT) // Sintesis streaming menggunakan PCM atau MP3.
                        .build();
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // Metode call dengan callback tidak memblokir thread saat ini.
        try {
            for (String text : textArray) {
                // Kirimkan segmen teks dan terima audio biner secara real-time dari metode onEvent antarmuka callback.
                synthesizer.streamingCall(text);
            }
            // Tunggu hingga sintesis ucapan streaming selesai.
            synthesizer.streamingComplete();
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Setelah tugas selesai, tutup koneksi WebSocket.
            synthesizer.getDuplexApi().close(1000, "bye");
        }

        // Koneksi WebSocket dibuat saat segmen teks pertama dikirim. Oleh karena itu, latensi paket pertama mencakup waktu pembuatan koneksi.
        System.out.println(
                "[Metric] Request ID: "
                        + synthesizer.getLastRequestId()
                        + ", First-packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) {
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}

ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
    @Override
    public void onEvent(SpeechSynthesisResult result) {
        System.out.println("RequestId: " + result.getRequestId());
        // Proses potongan audio secara real-time, misalnya untuk pemutaran atau menulis ke buffer.
    }

    @Override
    public void onComplete() {
        System.out.println("Task completed");
        // Tangani logika pasca-sintesis, seperti melepaskan pemutar.
    }

    @Override
    public void onError(Exception e) {
        System.out.println("Task failed: " + e.getMessage());
        // Tangani pengecualian, seperti kesalahan jaringan atau kode kesalahan sisi server.
    }
};