Alibaba Cloud Model Studio:CosyVoice speech synthesis Java SDK

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

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()
                        // The API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // If you have not configured environment variables, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model(model) // Model
                        .voice(voice) // Voice
                        .build();

        // Synchronous mode: Disable the 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 you send text 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) {
        // The following URL is for the Singapore region. If you use a model in the Beijing region, replace the URL with: wss://dashscope.aliyuncs.com/api-ws/v1/inference
        Constants.baseWebsocketApiUrl = "wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference";
        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 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 = "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 for saving 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 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()
                        // The API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // If you have not configured environment variables, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_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. The binary audio is returned 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 you send text 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) {
        // The following URL is for the Singapore region. If you use a model in the Beijing region, replace the URL with: wss://dashscope.aliyuncs.com/api-ws/v1/inference
        Constants.baseWebsocketApiUrl = "wss://dashscope-intl.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 = {"The streaming text-to-speech SDK ",
            "can convert input text ", "into binary audio data. ", "Compared to non-streaming synthesis, ",
            "streaming offers better real-time performance. ", "You can hear the audio output almost instantly as you type, ",
            "which greatly improves the user experience ", "and reduces waiting time. ",
            "This is ideal for applications that use large ", "language models (LLMs) ",
            "to synthesize speech from a stream of text."};
    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 for processing audio data here.
                    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("An exception occurred: " + e.toString());
            }
        };

        // Request parameters
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // The API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // If you have not configured environment variables, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model(model)
                        .voice(voice)
                        .format(SpeechSynthesisAudioFormat
                                .PCM_22050HZ_MONO_16BIT) // Use PCM or MP3 for streaming synthesis.
                        .build();
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // The call method with a callback will not block the current thread.
        try {
            for (String text : textArray) {
                // Send text fragments and get the binary audio in real time in 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 {
            // Close the WebSocket connection after the task is complete.
            synthesizer.getDuplexApi().close(1000, "bye");
        }

        // A WebSocket connection must be established when you send text 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) {
        // The following URL is for the Singapore region. If you use a model in the Beijing region, replace the URL with: wss://dashscope.aliyuncs.com/api-ws/v1/inference
        Constants.baseWebsocketApiUrl = "wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference";
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}

ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
    @Override
    public void onEvent(SpeechSynthesisResult result) {
        System.out.println("Request ID: " + result.getRequestId());
        // Process audio chunks in real time (e.g., play or write to a buffer).
    }

    @Override
    public void onComplete() {
        System.out.println("Task complete");
        // Handle synthesis completion logic (e.g., release the player).
    }

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