语音合成Sambert Java API

以下示例展示了如何使用同步接口调用发音人模型知厨（sambert-zhichu-v1），将文案“今天天气怎么样”合成采样率为48kHz，音频格式为wav的音频，并保存到名为output.wav的文件中。

import com.alibaba.dashscope.audio.tts.SpeechSynthesizer;
import com.alibaba.dashscope.audio.tts.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.tts.SpeechSynthesisAudioFormat;

import java.io.*;
import java.nio.ByteBuffer;

public class Main {
    public static void syncAudioDataToFile() {
        SpeechSynthesizer synthesizer = new SpeechSynthesizer();
        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apiKey替换为自己的API Key
                // .apiKey("yourApikey")
                .model("sambert-zhichu-v1")
                .text("今天天气怎么样")
                .sampleRate(48000)
                .format(SpeechSynthesisAudioFormat.WAV)
                .build();

        File file = new File("output.wav");
        // 提交同步合成任务，获取完整的音频数据
        ByteBuffer audio = synthesizer.call(param);
        try (FileOutputStream fos = new FileOutputStream(file)) {
            fos.write(audio.array());
            System.out.println("synthesis done!");
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

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

以下示例展示了如何使用流式接口调用发音人模型知厨（sambert-zhichu-v1）将文案“今天天气怎么样”合成采样率为48kHz，默认音频格式（wav）的流式音频，并获取对应时间戳。

import com.alibaba.dashscope.audio.tts.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.tts.SpeechSynthesisResult;
import com.alibaba.dashscope.audio.tts.SpeechSynthesizer;
import com.alibaba.dashscope.common.ResultCallback;

import java.util.concurrent.CountDownLatch;

public class Main {
    public static void main(String[] args) {
        CountDownLatch latch = new CountDownLatch(1);
        SpeechSynthesizer synthesizer = new SpeechSynthesizer();
        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apiKey替换为自己的API Key
                // .apiKey("yourApikey")
                .model("sambert-zhichu-v1")
                .text("今天天气怎么样")
                .sampleRate(48000)
                .enableWordTimestamp(true)
                .enablePhonemeTimestamp(true)
                .build();

        class ReactCallback extends ResultCallback<SpeechSynthesisResult> {
            @Override
            public void onEvent(SpeechSynthesisResult result) {
                if (result.getAudioFrame() != null) {
                    // do something with the audio frame
                    System.out.println("audio result length: " + result.getAudioFrame().array().length);
                }
                if (result.getTimestamp() != null) {
                    // do something with the timestamp
                    System.out.println("timestamp: " + result.getTimestamp());
                }
            }

            @Override
            public void onComplete() {
                // do something when the synthesis is done
                System.out.println("onComplete!");
                latch.countDown();
            }

            @Override
            public void onError(Exception e) {
                // do something when an error occurs
                System.out.println("onError:" + e);
                latch.countDown();
            }
        }

        synthesizer.call(param, new ReactCallback());
        try {
            latch.await();
        } catch (InterruptedException e) {
            throw new RuntimeException(e);
        }
        System.exit(0);
    }
}

以下示例展示了通过Flowable对象的blockingForEach接口，阻塞式地获取每次流式返回的SpeechSynthesisResult类型数据。

您也可以在Flowable的所有流式数据返回完成后，通过核心类（SpeechSynthesizer）的getAudioData和getTimestamps方法分别获取完整的合成结果和完整的时间戳。

import com.alibaba.dashscope.audio.tts.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.tts.SpeechSynthesisResult;
import com.alibaba.dashscope.audio.tts.SpeechSynthesizer;
import io.reactivex.Flowable;

public class Main {
    public static void main(String[] args) {
        SpeechSynthesizer synthesizer = new SpeechSynthesizer();
        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apiKey替换为自己的API Key
                // .apiKey("yourApikey")
                .model("sambert-zhichu-v1")
                .text("今天天气怎么样")
                .sampleRate(48000)
                .enableWordTimestamp(true)
                .build();

        Flowable<SpeechSynthesisResult> flowable = synthesizer.streamCall(param);
        flowable.blockingForEach(
                msg -> {
                    if (msg.getAudioFrame() != null) {
                        // do something with the audio frame
                        System.out.println("getAudioFrame");
                    }
                    if (msg.getTimestamp() != null) {
                        // do something with the timestamp
                        System.out.println("getTimestamp");
                    }
                }
        );
        System.exit(0);
    }
}

ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
    @Override
    public void onEvent(SpeechSynthesisResult result) {
        System.out.println("RequestId为：" + result.getRequestId());
        // 在此实现处理语音合成结果的逻辑
    }

    @Override
    public void onComplete() {
        System.out.println("任务完成");
    }

    @Override
    public void onError(Exception e) {
        System.out.println("任务失败：" + e.getMessage());
    }
};