语音合成CosyVoice Java API

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 {
    // 模型
    private static String model = "cosyvoice-v2";
    // 音色
    private static String voice = "longxiaochun_v2";

    public static void streamAudioDataToSpeaker() {
        // 请求参数
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // 若没有将API Key配置到环境变量中，需将下面这行代码注释放开，并将your-api-key替换为自己的API Key
                        // .apiKey("your-api-key")
                        .model(model) // 模型
                        .voice(voice) // 音色
                        .build();

        // 同步模式：禁用回调（第二个参数为null）
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
        // 阻塞直至音频返回 
        ByteBuffer audio = synthesizer.call("今天天气怎么样？");
        // 将音频数据保存到本地文件“output.mp3”中
        File file = new File("output.mp3");
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first package delay 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);
    }
}

以下示例，展示如何使用同步接口调用语音大模型CosyVoice的音色“龙小淳（longxiaochun）”，将文案“今天天气怎么样”合成采样率为22050Hz，音频格式为MP3的音频。

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 {
    // 模型
    private static String model = "cosyvoice-v2";
    // 音色
    private static String voice = "longxiaochun_v2";

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

        // 实现回调接口ResultCallback
        ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                // System.out.println("收到消息: " + result);
                if (result.getAudioFrame() != null) {
                    // 此处实现保存音频数据到本地的逻辑
                    System.out.println(TimeUtils.getTimestamp() + " 收到音频");
                }
            }

            @Override
            public void onComplete() {
                System.out.println(TimeUtils.getTimestamp() + " 收到Complete，语音合成结束");
                latch.countDown();
            }

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

        // 请求参数
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // 若没有将API Key配置到环境变量中，需将下面这行代码注释放开，并将your-api-key替换为自己的API Key
                        // .apiKey("your-api-key")
                        .model(model) // 模型
                        .voice(voice) // 音色
                        .build();
        // 第二个参数“callback”传入回调即启用异步模式
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // 非阻塞调用，立即返回null（实际结果通过回调接口异步传递），在回调接口的onEvent方法中实时获取二进制音频
        synthesizer.call("今天天气怎么样？");
        // 等待合成完成
        try {
            latch.await();
            // 等待播放线程全部播放完
        } catch (InterruptedException e) {
            throw new RuntimeException(e);
        }
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first package delay 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 = {"流式文本语音合成SDK，",
            "可以将输入的文本", "合成为语音二进制数据，", "相比于非流式语音合成，",
            "流式合成的优势在于实时性", "更强。用户在输入文本的同时",
            "可以听到接近同步的语音输出，", "极大地提升了交互体验，",
            "减少了用户等待时间。", "适用于调用大规模", "语言模型（LLM），以",
            "流式输入文本的方式", "进行语音合成的场景。"};
    private static String model = "cosyvoice-v2"; // 模型
    private static String voice = "longxiaochun_v2"; // 音色

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

        // 配置回调函数
        ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                // System.out.println("收到消息: " + result);
                if (result.getAudioFrame() != null) {
                    // 此处实现处理音频数据的逻辑
                    System.out.println(TimeUtils.getTimestamp() + " 收到音频");
                }
            }

            @Override
            public void onComplete() {
                System.out.println(TimeUtils.getTimestamp() + " 收到Complete，语音合成结束");
                latch.countDown();
            }

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

        // 请求参数
        SpeechSynthesisParam param =
                SpeechSynthesisParam.builder()
                        // 若没有将API Key配置到环境变量中，需将下面这行代码注释放开，并将your-api-key替换为自己的API Key
                        // .apiKey("your-api-key")
                        .model(model)
                        .voice(voice)
                        .format(SpeechSynthesisAudioFormat
                                .PCM_22050HZ_MONO_16BIT) // 流式合成使用PCM或者MP3
                        .build();
        SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
        // 带Callback的call方法将不会阻塞当前线程
        for (String text : textArray) {
            // 发送文本片段，在回调接口的onEvent方法中实时获取二进制音频
            synthesizer.streamingCall(text);
        }
        // 结束流式语音合成
        synthesizer.streamingComplete();
        System.out.println(
                "[Metric] requestId: "
                        + synthesizer.getLastRequestId()
                        + ", first package delay ms: "
                        + synthesizer.getFirstPackageDelay());
        // 等待合成完成
        try {
            latch.await();
            // 等待播放线程全部播放完
        } catch (InterruptedException e) {
            throw new RuntimeException(e);
        }
    }

    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为：" + result.getRequestId());
        // 实时处理音频分片（如播放/写入缓冲）
    }

    @Override
    public void onComplete() {
        System.out.println("任务完成");
        // 处理合成结束逻辑（如释放播放器）
    }

    @Override
    public void onError(Exception e) {
        System.out.println("任务失败：" + e.getMessage());
        // 处理异常（网络错误/服务端错误码）
    }
};