272 lines
13 KiB
Markdown
272 lines
13 KiB
Markdown
|
# 阿里云CosyVoice Java SDK 调用模板（参数+示例）
|
|||
|
|
## 一、前提条件
|
|||
|
|
1. 开通CosyVoice服务，获取API Key（建议配置到环境变量，避免硬编码）。
|
|||
|
|
2. 安装最新版DashScope SDK（支持2.20.3+版本，SSML功能需此版本及以上）。
|
|||
|
|
3. 模型与音色需匹配（如v2模型对应v2音色，v3模型对应v3音色）。
|
|||
|
|
|
|||
|
|
## 二、核心参数汇总
|
|||
|
|
| 参数名 | 类型 | 是否必填 | 默认值 | 取值范围/说明 |
|
|||
|
|
|--------------|------------|----------|-------------------------|------------------------------------------------------------------------------|
|
|||
|
|
| model | String | 是 | - | cosyvoice-v1/v2/v3/v3-plus（v3系列需申请邀测） |
|
|||
|
|
| voice | String | 是 | - | 对应模型的音色（如v2：longxiaochun_v2；v3：longhuohuo_v3，详见文档音色列表） |
|
|||
|
|
| format | enum | 否 | 因音色而异（默认MP3 22050Hz） | 支持WAV/MP3/PCM/OGG_OPUS，如PCM_22050HZ_MONO_16BIT、MP3_24000HZ_MONO_256KBPS |
|
|||
|
|
| volume | int | 否 | 50 | 0~100（音量大小） |
|
|||
|
|
| speechRate | float | 否 | 1.0 | 0.5~2.0（语速，1.0为默认，约4字/秒） |
|
|||
|
|
| pitchRate | float | 否 | 1.0 | 0.5~2.0（语调） |
|
|||
|
|
| bit_rate | int | 否 | 32 | 6~510kbps（仅opus格式支持，v1模型不支持） |
|
|||
|
|
| seed | int | 否 | 0 | 0~65535（随机数种子，仅v3/v3-plus支持） |
|
|||
|
|
| style | int | 否 | 0 | ≥0整数（风格调整，仅v3/v3-plus支持） |
|
|||
|
|
| languageHints| List<String> | 否 | - | 仅v3/v3-plus支持，单次配置1个语种（"zh"/"en"） |
|
|||
|
|
| instruction | String | 否 | - | 仅v3/v3-plus支持，格式："你说话的情感是<情感值>"（如"Happy"/"Angry"） |
|
|||
|
|
|
|||
|
|
## 三、四种核心调用方式模板
|
|||
|
|
### 1. 同步调用（阻塞式，适合短文本）
|
|||
|
|
```java
|
|||
|
|
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
|
|||
|
|
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
|
|||
|
|
import java.io.File;
|
|||
|
|
import java.io.FileOutputStream;
|
|||
|
|
import java.nio.ByteBuffer;
|
|||
|
|
|
|||
|
|
public class SyncCallTemplate {
|
|||
|
|
// 配置参数（根据需求修改）
|
|||
|
|
private static final String MODEL = "cosyvoice-v3"; // 模型
|
|||
|
|
private static final String VOICE = "longhuohuo_v3"; // 音色
|
|||
|
|
private static final String TEXT = "今天天气真好，适合出门散步！"; // ≤2000字符
|
|||
|
|
private static final String OUTPUT_FILE = "output.mp3"; // 输出文件
|
|||
|
|
|
|||
|
|
public static void main(String[] args) {
|
|||
|
|
// 1. 构建请求参数
|
|||
|
|
SpeechSynthesisParam param = SpeechSynthesisParam.builder()
|
|||
|
|
// .apiKey("your-api-key") // 未配置环境变量时打开
|
|||
|
|
.model(MODEL)
|
|||
|
|
.voice(VOICE)
|
|||
|
|
.volume(60) // 可选：调整音量
|
|||
|
|
.speechRate(1.1f) // 可选：调整语速
|
|||
|
|
.build();
|
|||
|
|
|
|||
|
|
// 2. 初始化合成器（同步调用传null）
|
|||
|
|
SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
|
|||
|
|
ByteBuffer audioData = null;
|
|||
|
|
|
|||
|
|
try {
|
|||
|
|
// 3. 阻塞调用，获取完整音频
|
|||
|
|
audioData = synthesizer.call(TEXT);
|
|||
|
|
// 4. 保存音频到本地
|
|||
|
|
if (audioData != null) {
|
|||
|
|
try (FileOutputStream fos = new FileOutputStream(new File(OUTPUT_FILE))) {
|
|||
|
|
fos.write(audioData.array());
|
|||
|
|
}
|
|||
|
|
System.out.println("合成成功！输出文件：" + OUTPUT_FILE);
|
|||
|
|
System.out.println("RequestId：" + synthesizer.getLastRequestId());
|
|||
|
|
System.out.println("首包延迟：" + synthesizer.getFirstPackageDelay() + "ms");
|
|||
|
|
}
|
|||
|
|
} catch (Exception e) {
|
|||
|
|
System.err.println("合成失败：" + e.getMessage());
|
|||
|
|
} finally {
|
|||
|
|
// 5. 关闭WebSocket连接
|
|||
|
|
synthesizer.getDuplexApi().close(1000, "任务结束");
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 2. 异步调用（非阻塞，短文本实时接收）
|
|||
|
|
```java
|
|||
|
|
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.util.concurrent.CountDownLatch;
|
|||
|
|
|
|||
|
|
public class AsyncCallTemplate {
|
|||
|
|
private static final String MODEL = "cosyvoice-v2";
|
|||
|
|
private static final String VOICE = "longxiaochun_v2";
|
|||
|
|
private static final String TEXT = "欢迎使用阿里云CosyVoice语音合成服务！"; // ≤2000字符
|
|||
|
|
|
|||
|
|
public static void main(String[] args) throws InterruptedException {
|
|||
|
|
CountDownLatch latch = new CountDownLatch(1);
|
|||
|
|
|
|||
|
|
// 1. 配置回调（实时接收音频）
|
|||
|
|
ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
|
|||
|
|
@Override
|
|||
|
|
public void onEvent(SpeechSynthesisResult result) {
|
|||
|
|
// 接收音频分片（可实时播放或写入文件）
|
|||
|
|
if (result.getAudioFrame() != null) {
|
|||
|
|
System.out.println("收到音频分片，大小：" + result.getAudioFrame().capacity() + "字节");
|
|||
|
|
// 此处可添加音频处理逻辑（如流式播放、追加写入文件）
|
|||
|
|
}
|
|||
|
|
// 查看计费字符数（最终以最后一次为准）
|
|||
|
|
if (result.getUsage() != null) {
|
|||
|
|
System.out.println("当前计费字符数：" + result.getUsage().getCharacters());
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
@Override
|
|||
|
|
public void onComplete() {
|
|||
|
|
System.out.println("合成完成！");
|
|||
|
|
latch.countDown();
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
@Override
|
|||
|
|
public void onError(Exception e) {
|
|||
|
|
System.err.println("合成失败：" + e.getMessage());
|
|||
|
|
latch.countDown();
|
|||
|
|
}
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
// 2. 构建参数并初始化合成器
|
|||
|
|
SpeechSynthesisParam param = SpeechSynthesisParam.builder()
|
|||
|
|
// .apiKey("your-api-key")
|
|||
|
|
.model(MODEL)
|
|||
|
|
.voice(VOICE)
|
|||
|
|
.format(SpeechSynthesisAudioFormat.MP3_16000HZ_MONO_128KBPS) // 可选配置格式
|
|||
|
|
.build();
|
|||
|
|
SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
|
|||
|
|
|
|||
|
|
try {
|
|||
|
|
// 3. 非阻塞调用
|
|||
|
|
synthesizer.call(TEXT);
|
|||
|
|
latch.await(); // 等待合成完成
|
|||
|
|
System.out.println("RequestId：" + synthesizer.getLastRequestId());
|
|||
|
|
} catch (Exception e) {
|
|||
|
|
System.err.println("调用异常：" + e.getMessage());
|
|||
|
|
} finally {
|
|||
|
|
synthesizer.getDuplexApi().close(1000, "任务结束");
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 3. 流式调用（分段传文本，适合长文本）
|
|||
|
|
```java
|
|||
|
|
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;
|
|||
|
|
|
|||
|
|
public class StreamingCallTemplate {
|
|||
|
|
// 分段文本（每段≤2000字符，累计≤20万字符）
|
|||
|
|
private static final String[] TEXT_SEGMENTS = {
|
|||
|
|
"流式语音合成适合长文本场景，",
|
|||
|
|
"可以分段发送文本，",
|
|||
|
|
"服务端实时返回音频，",
|
|||
|
|
"减少等待时间。"
|
|||
|
|
};
|
|||
|
|
private static final String MODEL = "cosyvoice-v3";
|
|||
|
|
private static final String VOICE = "longchuanshu_v3";
|
|||
|
|
|
|||
|
|
public static void main(String[] args) {
|
|||
|
|
// 1. 配置回调
|
|||
|
|
ResultCallback<SpeechSynthesisResult> callback = new ResultCallback<SpeechSynthesisResult>() {
|
|||
|
|
@Override
|
|||
|
|
public void onEvent(SpeechSynthesisResult result) {
|
|||
|
|
if (result.getAudioFrame() != null) {
|
|||
|
|
System.out.println("收到流式音频分片");
|
|||
|
|
// 处理音频（如实时播放、写入缓冲文件）
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
@Override
|
|||
|
|
public void onComplete() {
|
|||
|
|
System.out.println("流式合成全部完成！");
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
@Override
|
|||
|
|
public void onError(Exception e) {
|
|||
|
|
System.err.println("流式合成失败：" + e.getMessage());
|
|||
|
|
}
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
// 2. 构建参数
|
|||
|
|
SpeechSynthesisParam param = SpeechSynthesisParam.builder()
|
|||
|
|
// .apiKey("your-api-key")
|
|||
|
|
.model(MODEL)
|
|||
|
|
.voice(VOICE)
|
|||
|
|
.format(SpeechSynthesisAudioFormat.PCM_22050HZ_MONO_16BIT)
|
|||
|
|
.speechRate(0.9f)
|
|||
|
|
.build();
|
|||
|
|
SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, callback);
|
|||
|
|
|
|||
|
|
try {
|
|||
|
|
// 3. 分段发送文本（间隔≤23秒）
|
|||
|
|
for (String segment : TEXT_SEGMENTS) {
|
|||
|
|
synthesizer.streamingCall(segment);
|
|||
|
|
Thread.sleep(500); // 模拟文本输入间隔
|
|||
|
|
}
|
|||
|
|
// 4. 必须调用：结束流式合成（触发剩余文本合成）
|
|||
|
|
synthesizer.streamingComplete();
|
|||
|
|
System.out.println("RequestId：" + synthesizer.getLastRequestId());
|
|||
|
|
} catch (Exception e) {
|
|||
|
|
System.err.println("调用异常：" + e.getMessage());
|
|||
|
|
} finally {
|
|||
|
|
synthesizer.getDuplexApi().close(1000, "任务结束");
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 4. Flowable调用（响应式编程，支持流式输入输出）
|
|||
|
|
```java
|
|||
|
|
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
|
|||
|
|
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
|
|||
|
|
import com.alibaba.dashscope.exception.NoApiKeyException;
|
|||
|
|
import io.reactivex.Flowable;
|
|||
|
|
import io.reactivex.BackpressureStrategy;
|
|||
|
|
|
|||
|
|
public class FlowableCallTemplate {
|
|||
|
|
private static final String MODEL = "cosyvoice-v2";
|
|||
|
|
private static final String VOICE = "longyingtian_v2";
|
|||
|
|
private static final String[] TEXT_ARRAY = {"响应式编程模式，", "支持流式输入输出，", "适合高并发场景。"};
|
|||
|
|
|
|||
|
|
public static void main(String[] args) throws NoApiKeyException {
|
|||
|
|
// 1. 模拟流式文本输入
|
|||
|
|
Flowable<String> textStream = Flowable.create(emitter -> {
|
|||
|
|
new Thread(() -> {
|
|||
|
|
for (String text : TEXT_ARRAY) {
|
|||
|
|
emitter.onNext(text);
|
|||
|
|
try {
|
|||
|
|
Thread.sleep(800);
|
|||
|
|
} catch (InterruptedException e) {
|
|||
|
|
emitter.onError(e);
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
emitter.onComplete();
|
|||
|
|
}).start();
|
|||
|
|
}, BackpressureStrategy.BUFFER);
|
|||
|
|
|
|||
|
|
// 2. 构建参数
|
|||
|
|
SpeechSynthesisParam param = SpeechSynthesisParam.builder()
|
|||
|
|
// .apiKey("your-api-key")
|
|||
|
|
.model(MODEL)
|
|||
|
|
.voice(VOICE)
|
|||
|
|
.volume(70)
|
|||
|
|
.build();
|
|||
|
|
SpeechSynthesizer synthesizer = new SpeechSynthesizer(param, null);
|
|||
|
|
|
|||
|
|
try {
|
|||
|
|
// 3. 流式调用并处理结果
|
|||
|
|
synthesizer.streamingCallAsFlowable(textStream)
|
|||
|
|
.blockingForEach(result -> {
|
|||
|
|
if (result.getAudioFrame() != null) {
|
|||
|
|
System.out.println("Flowable收到音频，大小：" + result.getAudioFrame().capacity() + "字节");
|
|||
|
|
// 处理音频逻辑
|
|||
|
|
}
|
|||
|
|
});
|
|||
|
|
System.out.println("Flowable合成完成！RequestId：" + synthesizer.getLastRequestId());
|
|||
|
|
} finally {
|
|||
|
|
synthesizer.getDuplexApi().close(1000, "任务结束");
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 四、核心注意事项
|
|||
|
|
1. 文本长度限制：非流式单次≤2000字符，流式累计≤20万字符（含SSML标签）。
|
|||
|
|
2. 字符计算规则：汉字=2字符，英文/数字/标点/空格=1字符。
|
|||
|
|
3. 流式调用必须调用`streamingComplete()`，否则结尾文本无法合成。
|
|||
|
|
4. 每次调用`call()`前需重新初始化`SpeechSynthesizer`实例。
|
|||
|
|
5. 音频格式需与播放器兼容（如MP3/OPUS支持流式播放，推荐使用ffmpeg、AudioFormat等工具）。
|
|||
|
|
|