CosyVoice speech synthesis Java SDK

getBeginTime() - Get sentence start time

Method signature:

public int getBeginTime()

Return value: Sentence start time in milliseconds.

getEndTime() - Get sentence end time

Method signature:

public int getEndTime()

Return value: Sentence end time in milliseconds.

getWords() - Get word-level timestamps

Method signature:

public List<Word> getWords()

Return value: A List of Word objects containing word-level timestamp information. May be empty.

getBeginTime() - Get word start time

Method signature:

public int getBeginTime()

Return value: Word start time in milliseconds.

getEndTime() - Get word end time

Method signature:

public int getEndTime()

Return value: Word end time in milliseconds.

getText() - Get text

Method signature:

public String getText()

Return value: String, the text content.

getPhonemes() - Get phoneme-level timestamps

Method signature:

public List<Phoneme> getPhonemes()

Return value: A List of Phoneme objects containing phoneme-level timestamp information. May be empty.

getBeginTime() - Get phoneme start time

Method signature:

public int getBeginTime()

Return value: Phoneme start time in milliseconds.

getEndTime() - Get phoneme end time

Method signature:

public int getEndTime()

Return value: Phoneme end time in milliseconds.

getText() - Get text

Method signature:

public String getText()

Return value: String, the text content.

getTone() - Get tone

Method signature:

public int getTone()

Return value: The tone value.

• In English, 0, 1, and 2 represent unstressed, primary stress, and secondary stress respectively.

• In Chinese pinyin, 1, 2, 3, 4, and 5 represent the first, second, third, fourth, and neutral tones respectively.

• Non-streaming: A blocking call that sends the complete text at once and returns the full audio directly. Best suited for short-text speech synthesis.

• Unidirectional streaming: A non-blocking call that sends the complete text at once and delivers audio data (potentially in chunks) through a callback function. Best suited for short-text scenarios that require low latency.

• Bidirectional streaming: A non-blocking call that sends text in multiple segments and delivers incrementally synthesized audio through a callback function in real time. Best suited for long-text scenarios that require low latency.

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. Get an API Key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // If the environment variable is not configured, 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 callback (second parameter is null)
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
        ByteBuffer audio = null;
        try {
            // Block until 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 completed
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        if (audio != null) {
            // Save the audio data to a local file "output.mp3"
            File file = new File("output.mp3");
            // The first text transmission requires establishing a WebSocket connection, so the first packet latency includes the connection setup time
            System.out.println(
                    "[Metric] requestId: "
                            + 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 configuration is for the Singapore region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        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.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) {
                if (result.getAudioFrame() != null) {
                    // Implement the logic to save audio data locally here
                    System.out.println(TimeUtils.getTimestamp() + " Audio received");
                }
                // Get output information, including event type and original text
                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();
            }
        };

        // Request parameters
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // The API Keys for the Singapore and Beijing regions are different. Get an API Key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // If the environment variable is not configured, 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();
        // Passing "callback" as the second parameter enables asynchronous mode
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // Non-blocking call that returns null immediately (actual results are delivered asynchronously via the callback interface). Binary audio is received in real time through the onEvent method of the callback interface
        try {
            synthesizer.call("What's the weather like today?");
            // Wait for synthesis to complete
            latch.await();
            // Wait for playback thread to finish playing
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Close the WebSocket connection after the task is completed
            synthesizer.getDuplexApi().close(1000, "bye");
        }
        // The first text transmission requires establishing a WebSocket connection, so the first packet latency includes the connection setup time
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) {
        // The following configuration is for the Singapore region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        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 = "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 finished");
            }

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

        // Request parameters
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // The API Keys for the Singapore and Beijing regions are different. Get an API Key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                        // If the environment variable is not configured, 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 Callback will not block the current thread
        try {
            for (String text : textArray) {
                // Send text fragments and receive binary audio in real time through the onEvent method of the callback interface
                synthesizer.streamingCall(text);
            }
            // Wait for streaming speech synthesis to finish
            synthesizer.streamingComplete();
        } catch (Exception e) {
            throw new RuntimeException(e);
        } finally {
            // Close the WebSocket connection after the task is completed
            synthesizer.getDuplexApi().close(1000, "bye");
        }

        // The first text transmission requires establishing a WebSocket connection, so the first packet latency includes the connection setup time
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first packet latency (ms): "
                        + synthesizer.getFirstPackageDelay());
    }

    public static void main(String[] args) {
        // The following configuration is for the Singapore region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
        streamAudioDataToSpeaker();
        System.exit(0);
    }
}