Alibaba Cloud Model Studio:CosyVoice Java SDK for speech synthesis

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() {
        // Request parameters
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // If the API key is not configured as an environment variable, uncomment the following line and replace your-api-key with your API key.
                        // .apiKey("your-api-key")
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();

        // Synchronous mode: Disable callback (the second parameter is null).
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
        ByteBuffer audio = null;
        try {
            // Block until the audio is returned.
            audio = synthesizer.call("What's the weather like today?");
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Close the WebSocket connection after the task is complete.
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        if (audio != null) {
            // Save the audio data to a local file named "output.mp3".
            File file = new File("output.mp3");
            // A WebSocket connection must be established when the text is sent for the first time. Therefore, the first-packet latency includes the time required to establish the connection.
            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);

        // Implement the ResultCallback interface.
        ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                // System.out.println("Message received: " + result);
                if (result.getAudioFrame() != null) {
                    // Implement the logic to save the audio data to a local file here.
                    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();
            }
        };

        // Request parameters
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // If you have not configured the API key as an environment variable, uncomment the following line and replace "your-api-key" with your API key.
                        // .apiKey("your-api-key")
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();
        // Pass the callback as the second parameter to enable asynchronous mode.
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // This is a non-blocking call that returns null immediately. The actual result is passed asynchronously through the callback interface. Retrieve the binary audio in real time in the onEvent method of the callback interface.
        try {
            synthesizer.call("What's the weather like today?");
            // Wait for the synthesis to complete.
            latch.await();
            // Wait for all playback threads to finish.
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Close the WebSocket connection after the task is complete.
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        // A WebSocket connection must be established when the text is sent for the first time. Therefore, the first-packet latency includes the time required to establish the connection.
        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() {
        // Configure the callback function.
        ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                // System.out.println("Message received: " + result);
                if (result.getAudioFrame() != null) {
                    // Implement the logic to process audio data here.
                    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());
            }
        };

        // Request parameters
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // If the API key is not set as an environment variable, uncomment the following line and replace your-api-key with your key.
                        // .apiKey("your-api-key")
                        .model(model)
                        .voice(voice)
                        .format(SpeechSynthesisAudioFormat
                                .PCM_22050HZ_MONO_16BIT) // Streaming synthesis uses PCM or MP3.
                        .build();
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // The call method with a callback does not block the current thread.
        try {
            for (String text : textArray) {
                // Send text segments and receive binary audio in real time from the onEvent method of the callback interface.
                synthesizer.streamingCall(text);
            }
            // Wait for the streaming speech synthesis to complete.
            synthesizer.streamingComplete();
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // After the task is complete, close the WebSocket connection.
            synthesizer.getDuplexApi().close(1000, "bye");
        }

        // A WebSocket connection is established when the first text segment is sent. Therefore, the first-packet latency includes the connection establishment time.
        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());
        // Process audio shards in real time, such as for playback or writing to a buffer.
    }

    @Override
    public void onComplete() {
        System.out.println("Task completed");
        // Handle post-synthesis logic, such as releasing the player.
    }

    @Override
    public void onError(Exception e) {
        System.out.println("Task failed: " + e.getMessage());
        // Handle exceptions, such as network errors or server-side error codes.
    }
};