feat: 功能优化
This commit is contained in:
129
docs/cosyvoice-copy.md
Normal file
129
docs/cosyvoice-copy.md
Normal file
@@ -0,0 +1,129 @@
|
||||
# 阿里云CosyVoice声音复刻API说明文档
|
||||
## 一、接口概述
|
||||
CosyVoice声音复刻API依托大模型技术,仅需10~20秒清晰音频,即可快速生成高度拟真的定制音色(`voice_id`),支持`cosyvoice-v1`和`cosyvoice-v2`模型(v2效果更优)。复刻服务免费,使用复刻音色进行语音合成时按字符计费。
|
||||
|
||||
核心功能:音色的创建、查询、更新、删除,生成的`voice_id`可直接用于CosyVoice语音合成接口。
|
||||
|
||||
## 二、前提条件
|
||||
1. 开通CosyVoice服务,获取API Key(推荐配置到环境变量,避免硬编码)。
|
||||
2. 安装最新版DashScope SDK(Java/Python),其他语言需调用RESTful API。
|
||||
3. 准备公网可访问的音频URL(推荐上传至阿里云OSS,支持WAV/MP3/M4A格式)。
|
||||
|
||||
## 三、核心接口详情(支持Java/Python SDK + RESTful API)
|
||||
### 1. 创建音色(生成voice_id)
|
||||
#### 功能描述
|
||||
上传10~20秒音频,生成专属`voice_id`,用于后续语音合成。
|
||||
#### 请求参数
|
||||
| 参数名 | 类型 | 是否必填 | 说明 |
|
||||
|--------------|--------|----------|----------------------------------------------------------------------|
|
||||
| target_model | string | 是 | 复刻模型,支持`cosyvoice-v1`/`cosyvoice-v2` |
|
||||
| prefix | string | 是 | 音色自定义前缀,仅允许数字和小写字母,长度<10字符 |
|
||||
| url | string | 是 | 音频文件公网URL,需满足格式要求(采样率≥16kHz、文件≤10MB、含≥5秒连续语音) |
|
||||
#### 响应参数
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|----------|--------|--------------------------|
|
||||
| voice_id | string | 定制音色ID,用于语音合成 |
|
||||
| request_id| string | 任务唯一标识,用于排查问题 |
|
||||
#### 示例代码(Python SDK)
|
||||
```python
|
||||
import os
|
||||
import dashscope
|
||||
from dashscope.audio.tts_v2 import VoiceEnrollmentService
|
||||
|
||||
dashscope.api_key = os.getenv('DASHSCOPE_API_KEY')
|
||||
service = VoiceEnrollmentService()
|
||||
# 调用创建接口
|
||||
voice_id = service.create_voice(target_model="cosyvoice-v2", prefix="test", url="音频公网URL")
|
||||
print(f"生成的voice_id: {voice_id}")
|
||||
```
|
||||
|
||||
### 2. 查询所有音色
|
||||
#### 功能描述
|
||||
查询账号下已创建的所有音色,支持按前缀筛选和分页。
|
||||
#### 请求参数
|
||||
| 参数名 | 类型 | 是否必填 | 说明 |
|
||||
|------------|--------|----------|-------------------------------|
|
||||
| prefix | string | 否 | 音色前缀,为空则返回所有音色 |
|
||||
| page_index | int | 否 | 页码索引,默认0 |
|
||||
| page_size | int | 否 | 每页条数,默认10 |
|
||||
#### 响应参数
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|--------------|--------|----------------------------------------------------------------------|
|
||||
| voice_list | array | 音色列表,含每个音色的`voice_id`、创建时间(gmt_create)、状态(status) |
|
||||
| status | string | 音色状态:DEPLOYING(审核中)/OK(可用)/UNDEPLOYED(审核失败) |
|
||||
| request_id | string | 任务唯一标识 |
|
||||
|
||||
### 3. 查询指定音色
|
||||
#### 功能描述
|
||||
查询单个`voice_id`的详细信息(状态、原始音频URL等)。
|
||||
#### 请求参数
|
||||
| 参数名 | 类型 | 是否必填 | 说明 |
|
||||
|----------|--------|----------|--------------------|
|
||||
| voice_id | string | 是 | 需查询的音色ID |
|
||||
#### 响应参数
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|----------------|--------|----------------------------------------------------------------------|
|
||||
| voice_id | string | 音色ID |
|
||||
| resource_link | string | 复刻所用音频的公网URL |
|
||||
| target_model | string | 复刻时使用的模型 |
|
||||
| status | string | 音色状态(DEPLOYING/OK/UNDEPLOYED) |
|
||||
| gmt_create | string | 音色创建时间 |
|
||||
|
||||
### 4. 更新音色
|
||||
#### 功能描述
|
||||
使用新的音频URL更新已有`voice_id`的音色。
|
||||
#### 请求参数
|
||||
| 参数名 | 类型 | 是否必填 | 说明 |
|
||||
|----------|--------|----------|----------------------------------------------------------------------|
|
||||
| voice_id | string | 是 | 需更新的音色ID |
|
||||
| url | string | 是 | 新的音频公网URL(需满足格式要求) |
|
||||
#### 响应参数
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|------------|--------|--------------------|
|
||||
| request_id | string | 任务唯一标识 |
|
||||
|
||||
### 5. 删除音色
|
||||
#### 功能描述
|
||||
删除无需使用的`voice_id`,释放配额(账号最多保留1000个音色)。
|
||||
#### 请求参数
|
||||
| 参数名 | 类型 | 是否必填 | 说明 |
|
||||
|----------|--------|----------|--------------------|
|
||||
| voice_id | string | 是 | 需删除的音色ID |
|
||||
#### 响应参数
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|------------|--------|--------------------|
|
||||
| request_id | string | 任务唯一标识 |
|
||||
|
||||
## 四、音频文件要求
|
||||
1. 格式:支持WAV(16bit)、MP3、M4A。
|
||||
2. 采样率:≥16000Hz。
|
||||
3. 时长:10~20秒(建议不超过60秒),含至少一段≥5秒的连续语音。
|
||||
4. 大小:≤10MB。
|
||||
5. 质量:语音清晰、无杂音,朗读连贯。
|
||||
|
||||
## 五、使用流程(复刻→合成)
|
||||
1. 调用「创建音色」接口,传入音频URL,获取`voice_id`。
|
||||
2. 调用CosyVoice语音合成接口,将`voice_id`作为`voice`参数传入,即可使用定制音色合成语音。
|
||||
3. (可选)通过「查询指定音色」接口确认`status`为`OK`后再使用。
|
||||
|
||||
## 六、关键限制
|
||||
1. 配额限制:每个主账号最多保留1000个复刻音色,删除后释放配额。
|
||||
2. 并发限制:复刻接口总并发≤10 RPS(v1+v2合计),语音合成接口并发≤3 RPS。
|
||||
3. 模型匹配:v1版本`voice_id`仅用于v1合成,v2版本`voice_id`仅用于v2合成,不可混用。
|
||||
4. 有效期:超过1年未使用的音色将自动下线。
|
||||
|
||||
## 七、常见错误码及解决方案
|
||||
| 错误码 | 说明 | 解决方案 |
|
||||
|-------------------------|---------------------------------------|------------------------------------------------------------------|
|
||||
| Throttling.AllocationQuota | 音色数量达限额 | 删除无用音色或提交工单申请扩容 |
|
||||
| Audio.AudioShortError | 音频有效时长过短 | 重新录制10~20秒连续语音 |
|
||||
| InvalidApiKey | API Key无效 | 检查API Key是否正确,无多余空格或缺失字符 |
|
||||
| Model.AccessDenied | 模型访问权限不足 | 使用“默认业务空间”下的API Key调用 |
|
||||
| BadRequest.UnsupportedFileFormat | 音频格式不支持 | 转换为WAV/MP3/M4A格式,确认文件实际编码与后缀一致 |
|
||||
| Audio.FileSizeExceed | 音频文件超过10MB | 压缩文件大小或截取有效片段 |
|
||||
|
||||
## 八、注意事项
|
||||
1. 版权要求:需对复刻音频的所有权及合法使用权负责,遵守服务协议。
|
||||
2. 音频URL:确保公网可访问,推荐使用阿里云OSS生成临时访问链接(避免长期公开泄露)。
|
||||
3. 升级建议:v1音色可使用原始音频重新复刻为v2版本,获得更优效果。
|
||||
4. 合成调节:使用`voice_id`合成语音时,可通过`volume`(音量)、`speechRate`(语速)等参数调节输出效果。
|
||||
271
docs/cosyvoice-generate.md
Normal file
271
docs/cosyvoice-generate.md
Normal file
@@ -0,0 +1,271 @@
|
||||
# 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)。
|
||||
|
||||
156
docs/cosyvoice-ram-config.md
Normal file
156
docs/cosyvoice-ram-config.md
Normal file
@@ -0,0 +1,156 @@
|
||||
# CosyVoice访问OSS配置指南
|
||||
|
||||
## 问题说明
|
||||
CosyVoice复刻服务需要访问OSS存储的音频文件,但默认情况下CosyVoice没有访问用户OSS的权限。
|
||||
|
||||
## 解决方案:配置RAM权限
|
||||
|
||||
### 1. 创建RAM角色
|
||||
在阿里云RAM控制台创建角色,允许CosyVoice服务访问OSS:
|
||||
|
||||
```json
|
||||
{
|
||||
"Version": "1",
|
||||
"Statement": [
|
||||
{
|
||||
"Effect": "Allow",
|
||||
"Action": [
|
||||
"oss:GetObject",
|
||||
"oss:HeadObject"
|
||||
],
|
||||
"Resource": [
|
||||
"acs:oss:*:*:{bucket-name}/*"
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
- `{bucket-name}`:替换为你的OSS存储桶名称
|
||||
|
||||
### 2. 配置信任策略
|
||||
为RAM角色添加信任策略,允许DashScope服务扮演该角色:
|
||||
|
||||
```json
|
||||
{
|
||||
"Version": "1",
|
||||
"Statement": [
|
||||
{
|
||||
"Effect": "Allow",
|
||||
"Principal": {
|
||||
"Service": [
|
||||
"dashscope.aliyuncs.com"
|
||||
]
|
||||
},
|
||||
"Action": "sts:AssumeRole"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
### 3. 授权步骤(控制台操作)
|
||||
|
||||
**步骤1:创建自定义权限策略**
|
||||
1. 登录阿里云控制台 → 访问控制(RAM) → 权限管理 → 权限策略
|
||||
2. 点击"创建策略"
|
||||
3. 选择"脚本配置"
|
||||
4. 粘贴上述JSON权限策略
|
||||
5. 策略名称:`CosyVoice-OSS-Access`
|
||||
6. 点击"确定"
|
||||
|
||||
**步骤2:创建RAM角色**
|
||||
1. RAM → 身份管理 → 角色 → 创建角色
|
||||
2. 选择"阿里云服务" → "DashScope"
|
||||
3. 输入角色名称:`CosyVoice-OSS-Role`
|
||||
4. 完成创建
|
||||
|
||||
**步骤3:授权角色访问OSS**
|
||||
1. 在角色详情页面,点击"添加权限"
|
||||
2. 搜索并添加:
|
||||
- `AliyunOSSReadOnlyAccess`(阿里云OSS只读权限)
|
||||
- `CosyVoice-OSS-Access`(自定义权限)
|
||||
3. 点击"确定"
|
||||
|
||||
**步骤4:获取ARN**
|
||||
在角色详情页面,复制"ARN":
|
||||
```
|
||||
acs:ram::{你的AccountID}:role/CosyVoice-OSS-Role
|
||||
```
|
||||
|
||||
### 4. 配置application.yaml
|
||||
|
||||
在 `yudao-server/src/main/resources/application.yaml` 中添加:
|
||||
|
||||
```yaml
|
||||
yudao:
|
||||
cosyvoice:
|
||||
# ... 其他配置
|
||||
# RAM角色ARN(用于授权CosyVoice访问OSS)
|
||||
ram-role-arn: "acs:ram::{AccountID}:role/CosyVoice-OSS-Role"
|
||||
```
|
||||
|
||||
### 5. 修改OSS访问方式
|
||||
|
||||
在 `CosyVoiceClient.buildClonePayload()` 中,添加授权信息:
|
||||
|
||||
```java
|
||||
// 在请求头中添加Authorization
|
||||
Request httpRequest = new Request.Builder()
|
||||
.url(properties.getVoiceEnrollmentUrl())
|
||||
.addHeader("Authorization", "Bearer " + properties.getApiKey())
|
||||
.addHeader("Content-Type", "application/json")
|
||||
// 添加STS临时凭证(需要先调用AssumeRole获取临时凭证)
|
||||
.addHeader("x-acs-security-token", "{security-token}")
|
||||
.post(RequestBody.create(payload.getBytes(StandardCharsets.UTF_8), JSON))
|
||||
.build();
|
||||
```
|
||||
|
||||
### 6. 获取STS临时凭证(Java代码)
|
||||
|
||||
```java
|
||||
import com.aliyun.sts20150401.Client;
|
||||
import com.aliyun.sts20150401.models.AssumeRoleRequest;
|
||||
import com.aliyun.sts20150401.models.AssumeRoleResponse;
|
||||
|
||||
public String getSecurityToken() {
|
||||
// 需要配置RAM角色ARN和访问密钥
|
||||
AssumeRoleRequest request = new AssumeRoleRequest()
|
||||
.setRoleArn(properties.getRamRoleArn())
|
||||
.setRoleSessionName("cosyvoice-session");
|
||||
|
||||
AssumeRoleResponse response = client.assumeRole(request);
|
||||
return response.body.credentials.securityToken;
|
||||
}
|
||||
```
|
||||
|
||||
### 7. 完整实现思路
|
||||
|
||||
1. **本地开发**:使用STS临时凭证
|
||||
2. **生产环境**:
|
||||
- 方案A:配置RAM角色,让CosyVoice直接访问OSS
|
||||
- 方案B:将音频文件上传到CosyVoice可访问的公共OSS存储桶
|
||||
|
||||
## 替代方案:使用公共OSS存储桶
|
||||
|
||||
如果RAM权限配置复杂,可以:
|
||||
|
||||
1. 创建公共可读的OSS存储桶
|
||||
2. 将音频文件上传到该存储桶
|
||||
3. 使用公共URL进行复刻
|
||||
|
||||
**注意**:公共存储桶存在安全风险,仅用于测试!
|
||||
|
||||
## 验证配置
|
||||
|
||||
配置完成后,重新测试语音复刻功能:
|
||||
|
||||
1. 查看日志中的请求URL是否可公网访问
|
||||
2. 查看是否还有"url error"错误
|
||||
3. 查看复刻是否成功返回voice_id
|
||||
|
||||
## 参考资料
|
||||
|
||||
- [阿里云RAM权限管理](https://help.aliyun.com/zh/ram/instance/role/parameter-overview)
|
||||
- [STS临时凭证](https://help.aliyun.com/zh/acs/STS/usage-scenarios/usage-scenarios)
|
||||
- [CosyVoice错误代码](https://help.aliyun.com/zh/model-studio/error-code#error-url)
|
||||
@@ -39,9 +39,6 @@
|
||||
<div v-if="column.key === 'name'" class="voice-name">
|
||||
{{ record.name || '未命名' }}
|
||||
</div>
|
||||
<div v-else-if="column.key === 'transcription'" class="transcription-text">
|
||||
{{ formatTranscription(record.transcription) }}
|
||||
</div>
|
||||
<span v-else-if="column.key === 'createTime'">
|
||||
{{ formatDateTime(record.createTime) }}
|
||||
</span>
|
||||
@@ -51,15 +48,6 @@
|
||||
</a-button>
|
||||
<a-space v-else-if="column.key === 'actions'">
|
||||
<a-button type="link" size="small" @click="handleEdit(record)">编辑</a-button>
|
||||
<a-button
|
||||
type="link"
|
||||
size="small"
|
||||
:loading="transcribingId === record.id"
|
||||
:disabled="!!record.transcription"
|
||||
@click="handleTranscribe(record)"
|
||||
>
|
||||
{{ record.transcription ? '已识别' : '识别' }}
|
||||
</a-button>
|
||||
<a-button type="link" size="small" danger @click="handleDelete(record)">删除</a-button>
|
||||
</a-space>
|
||||
</template>
|
||||
@@ -109,14 +97,6 @@
|
||||
<a-form-item label="备注" name="note">
|
||||
<a-textarea v-model="formData.note" :rows="3" placeholder="请输入备注信息" />
|
||||
</a-form-item>
|
||||
|
||||
<a-form-item v-if="!isCreateMode" label="识别内容" name="transcription">
|
||||
<a-textarea
|
||||
v-model="formData.transcription"
|
||||
:rows="4"
|
||||
placeholder="识别内容,支持手动修改"
|
||||
/>
|
||||
</a-form-item>
|
||||
</a-form>
|
||||
</a-modal>
|
||||
|
||||
@@ -125,7 +105,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { ref, reactive, computed, onMounted, onUnmounted, nextTick } from 'vue'
|
||||
import { ref, reactive, computed, onMounted, nextTick } from 'vue'
|
||||
import { message, Modal } from 'ant-design-vue'
|
||||
import { PlusOutlined, SearchOutlined, UploadOutlined, PlayCircleOutlined } from '@ant-design/icons-vue'
|
||||
import { VoiceService } from '@/api/voice'
|
||||
@@ -133,12 +113,6 @@ import { MaterialService } from '@/api/material'
|
||||
import dayjs from 'dayjs'
|
||||
|
||||
// ========== 常量 ==========
|
||||
const POLLING_CONFIG = {
|
||||
interval: 10000,
|
||||
maxCount: 30,
|
||||
transcriptionMaxLength: 50
|
||||
}
|
||||
|
||||
const DEFAULT_FORM_DATA = {
|
||||
id: null,
|
||||
name: '',
|
||||
@@ -146,8 +120,7 @@ const DEFAULT_FORM_DATA = {
|
||||
autoTranscribe: true,
|
||||
language: 'zh-CN',
|
||||
gender: 'female',
|
||||
note: '',
|
||||
transcription: ''
|
||||
note: ''
|
||||
}
|
||||
|
||||
// ========== 响应式数据 ==========
|
||||
@@ -155,13 +128,11 @@ const loading = ref(false)
|
||||
const submitting = ref(false)
|
||||
const uploading = ref(false)
|
||||
const voiceList = ref([])
|
||||
const transcribingId = ref(null)
|
||||
const modalVisible = ref(false)
|
||||
const formMode = ref('create')
|
||||
const formRef = ref(null)
|
||||
const audioPlayer = ref(null)
|
||||
const fileList = ref([])
|
||||
let pollingTimer = null
|
||||
|
||||
const searchParams = reactive({
|
||||
name: '',
|
||||
@@ -185,7 +156,6 @@ const isCreateMode = computed(() => formMode.value === 'create')
|
||||
// ========== 表格配置 ==========
|
||||
const columns = [
|
||||
{ title: '配音名称', key: 'name', dataIndex: 'name', width: 200 },
|
||||
{ title: '识别内容', key: 'transcription', dataIndex: 'transcription', width: 300 },
|
||||
{ title: '创建时间', key: 'createTime', dataIndex: 'createTime', width: 180 },
|
||||
{ title: '操作', key: 'actions', width: 200, fixed: 'right' }
|
||||
]
|
||||
@@ -197,12 +167,6 @@ const formRules = {
|
||||
}
|
||||
|
||||
// ========== 工具函数 ==========
|
||||
const formatTranscription = (transcription) => {
|
||||
if (!transcription) return '未识别'
|
||||
if (transcription.length <= POLLING_CONFIG.transcriptionMaxLength) return transcription
|
||||
return transcription.substring(0, POLLING_CONFIG.transcriptionMaxLength) + '...'
|
||||
}
|
||||
|
||||
const formatDateTime = (value) => {
|
||||
if (!value) return '-'
|
||||
return dayjs(value).format('YYYY-MM-DD HH:mm:ss')
|
||||
@@ -215,8 +179,7 @@ const fillFormData = (data) => {
|
||||
fileId: data.fileId || null,
|
||||
language: data.language || 'zh-CN',
|
||||
gender: data.gender || 'female',
|
||||
note: data.note || '',
|
||||
transcription: data.transcription || ''
|
||||
note: data.note || ''
|
||||
})
|
||||
}
|
||||
|
||||
@@ -300,62 +263,6 @@ const handleDelete = (record) => {
|
||||
})
|
||||
}
|
||||
|
||||
// ========== 语音识别 ==========
|
||||
const handleTranscribe = async (record) => {
|
||||
transcribingId.value = record.id
|
||||
try {
|
||||
const res = await VoiceService.transcribe(record.id)
|
||||
if (res.code !== 0) {
|
||||
message.error(res.msg || '识别失败')
|
||||
transcribingId.value = null
|
||||
return
|
||||
}
|
||||
|
||||
message.success('识别任务已提交,正在识别中...')
|
||||
startPollingTranscription(record.id)
|
||||
} catch (error) {
|
||||
console.error('识别失败:', error)
|
||||
message.error('识别失败,请稍后重试')
|
||||
transcribingId.value = null
|
||||
}
|
||||
}
|
||||
|
||||
const stopPolling = () => {
|
||||
if (pollingTimer) {
|
||||
clearInterval(pollingTimer)
|
||||
pollingTimer = null
|
||||
}
|
||||
transcribingId.value = null
|
||||
}
|
||||
|
||||
const startPollingTranscription = (voiceId) => {
|
||||
stopPolling()
|
||||
|
||||
let pollCount = 0
|
||||
pollingTimer = setInterval(async () => {
|
||||
pollCount++
|
||||
|
||||
try {
|
||||
const res = await VoiceService.get(voiceId)
|
||||
if (res.code === 0 && res.data?.transcription) {
|
||||
stopPolling()
|
||||
message.success('识别完成')
|
||||
loadVoiceList()
|
||||
return
|
||||
}
|
||||
|
||||
if (pollCount >= POLLING_CONFIG.maxCount) {
|
||||
stopPolling()
|
||||
message.warning('识别超时,请稍后手动刷新查看结果')
|
||||
loadVoiceList()
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('轮询识别结果失败:', error)
|
||||
if (pollCount >= POLLING_CONFIG.maxCount) stopPolling()
|
||||
}
|
||||
}, POLLING_CONFIG.interval)
|
||||
}
|
||||
|
||||
// ========== 音频播放 ==========
|
||||
const handlePlayAudio = (record) => {
|
||||
if (record.fileUrl && audioPlayer.value) {
|
||||
@@ -460,8 +367,7 @@ const handleSubmit = async () => {
|
||||
name: formData.name,
|
||||
language: formData.language,
|
||||
gender: formData.gender,
|
||||
note: formData.note,
|
||||
transcription: formData.transcription
|
||||
note: formData.note
|
||||
}
|
||||
|
||||
try {
|
||||
@@ -476,12 +382,6 @@ const handleSubmit = async () => {
|
||||
|
||||
message.success(isCreateMode.value ? '创建成功' : '更新成功')
|
||||
modalVisible.value = false
|
||||
|
||||
if (isCreateMode.value && formData.autoTranscribe && res.data) {
|
||||
message.info('自动识别已启动,正在识别中...')
|
||||
startPollingTranscription(res.data)
|
||||
}
|
||||
|
||||
loadVoiceList()
|
||||
} catch (error) {
|
||||
console.error('提交失败:', error)
|
||||
@@ -506,10 +406,6 @@ const resetForm = () => {
|
||||
onMounted(() => {
|
||||
loadVoiceList()
|
||||
})
|
||||
|
||||
onUnmounted(() => {
|
||||
stopPolling()
|
||||
})
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
@@ -550,12 +446,6 @@ onUnmounted(() => {
|
||||
color: var(--color-text);
|
||||
}
|
||||
|
||||
.transcription-text {
|
||||
color: var(--color-text-secondary);
|
||||
font-size: 13px;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
.upload-hint {
|
||||
font-size: 12px;
|
||||
color: var(--color-text-secondary);
|
||||
|
||||
@@ -3,9 +3,15 @@ package cn.iocoder.yudao.module.tik.voice.client;
|
||||
import cn.hutool.core.collection.CollUtil;
|
||||
import cn.hutool.core.util.StrUtil;
|
||||
import cn.iocoder.yudao.framework.common.exception.ServiceException;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceCloneRequest;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceCloneResult;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceTtsRequest;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceTtsResult;
|
||||
import cn.iocoder.yudao.module.tik.voice.config.CosyVoiceProperties;
|
||||
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
|
||||
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
|
||||
import com.alibaba.dashscope.audio.ttsv2.enrollment.Voice;
|
||||
import com.alibaba.dashscope.audio.ttsv2.enrollment.VoiceEnrollmentService;
|
||||
import com.fasterxml.jackson.databind.JsonNode;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import lombok.RequiredArgsConstructor;
|
||||
@@ -17,6 +23,7 @@ import okhttp3.RequestBody;
|
||||
import okhttp3.Response;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.nio.ByteBuffer;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.time.Duration;
|
||||
import java.util.Base64;
|
||||
@@ -53,8 +60,73 @@ public class CosyVoiceClient {
|
||||
if (request == null || StrUtil.isBlank(request.getText())) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "TTS 文本不能为空");
|
||||
}
|
||||
if (StrUtil.isBlank(request.getVoiceId())) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "必须提供 voiceId");
|
||||
}
|
||||
|
||||
SpeechSynthesizer synthesizer = null;
|
||||
try {
|
||||
log.info("[CosyVoice][开始TTS][voiceId={}, textLength={}, model={}]",
|
||||
request.getVoiceId(),
|
||||
request.getText().length(),
|
||||
StrUtil.blankToDefault(request.getModel(), properties.getDefaultModel()));
|
||||
|
||||
// 使用 DashScope SDK 构建参数(严格按文档)
|
||||
SpeechSynthesisParam param = SpeechSynthesisParam.builder()
|
||||
.apiKey(properties.getApiKey())
|
||||
.model(StrUtil.blankToDefault(request.getModel(), properties.getDefaultModel()))
|
||||
.voice(request.getVoiceId())
|
||||
.build();
|
||||
|
||||
// 初始化合成器(同步调用传 null)
|
||||
synthesizer = new SpeechSynthesizer(param, null);
|
||||
|
||||
// 阻塞调用,获取完整音频
|
||||
ByteBuffer audioData = synthesizer.call(request.getText());
|
||||
|
||||
if (audioData == null) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "CosyVoice 返回空音频数据");
|
||||
}
|
||||
|
||||
// 转换为字节数组(严格按照文档:直接使用 array())
|
||||
byte[] audioBytes = audioData.array();
|
||||
|
||||
log.info("[CosyVoice][TTS合成成功][Request ID: {}, audioSize={}, 首包延迟={}ms]",
|
||||
synthesizer.getLastRequestId(),
|
||||
audioBytes.length,
|
||||
synthesizer.getFirstPackageDelay());
|
||||
|
||||
// 构建返回结果
|
||||
CosyVoiceTtsResult result = new CosyVoiceTtsResult();
|
||||
result.setAudio(audioBytes);
|
||||
result.setFormat(request.getAudioFormat() != null ? request.getAudioFormat() : properties.getAudioFormat());
|
||||
result.setSampleRate(request.getSampleRate() != null ? request.getSampleRate() : properties.getSampleRate());
|
||||
result.setRequestId(synthesizer.getLastRequestId());
|
||||
result.setVoiceId(request.getVoiceId());
|
||||
|
||||
return result;
|
||||
|
||||
} catch (ServiceException ex) {
|
||||
throw ex;
|
||||
} catch (Exception ex) {
|
||||
log.error("[CosyVoice][TTS异常][voiceId={}, text={}]", request.getVoiceId(), request.getText(), ex);
|
||||
throw exception(VOICE_TTS_FAILED);
|
||||
} finally {
|
||||
// 关闭 WebSocket 连接
|
||||
if (synthesizer != null) {
|
||||
try {
|
||||
synthesizer.getDuplexApi().close(1000, "任务结束");
|
||||
} catch (Exception e) {
|
||||
log.warn("[CosyVoice][关闭连接失败]", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 使用 HTTP API 进行 TTS 合成(备用方案)
|
||||
*/
|
||||
private CosyVoiceTtsResult synthesizeViaHttp(CosyVoiceTtsRequest request) throws Exception {
|
||||
String payload = objectMapper.writeValueAsString(buildPayload(request));
|
||||
Request httpRequest = new Request.Builder()
|
||||
.url(properties.getTtsUrl())
|
||||
@@ -71,10 +143,47 @@ public class CosyVoiceClient {
|
||||
}
|
||||
return parseTtsResult(body, request);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 调用 CosyVoice 语音复刻接口(声音注册)
|
||||
*/
|
||||
public CosyVoiceCloneResult cloneVoice(CosyVoiceCloneRequest request) {
|
||||
if (!properties.isEnabled()) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "未配置 CosyVoice API Key");
|
||||
}
|
||||
if (request == null || StrUtil.isBlank(request.getUrl())) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "复刻音频URL不能为空");
|
||||
}
|
||||
if (request == null || StrUtil.isBlank(request.getTargetModel())) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "复刻模型不能为空");
|
||||
}
|
||||
if (request == null || StrUtil.isBlank(request.getPrefix())) {
|
||||
throw exception0(VOICE_TTS_FAILED.getCode(), "音色前缀不能为空");
|
||||
}
|
||||
|
||||
try {
|
||||
log.info("[CosyVoice][开始语音复刻][targetModel={}, prefix={}, url={}]",
|
||||
request.getTargetModel(), request.getPrefix(), request.getUrl());
|
||||
|
||||
// 使用 DashScope SDK 创建语音复刻
|
||||
VoiceEnrollmentService service = new VoiceEnrollmentService(properties.getApiKey());
|
||||
Voice voice = service.createVoice(request.getTargetModel(), request.getPrefix(), request.getUrl());
|
||||
|
||||
log.info("[CosyVoice][语音复刻成功][Request ID: {}, Voice ID: {}]",
|
||||
service.getLastRequestId(), voice.getVoiceId());
|
||||
|
||||
// 构建返回结果
|
||||
CosyVoiceCloneResult result = new CosyVoiceCloneResult();
|
||||
result.setVoiceId(voice.getVoiceId());
|
||||
result.setRequestId(service.getLastRequestId());
|
||||
|
||||
return result;
|
||||
} catch (ServiceException ex) {
|
||||
throw ex;
|
||||
} catch (Exception ex) {
|
||||
log.error("[CosyVoice][TTS异常]", ex);
|
||||
log.error("[CosyVoice][语音复刻异常][targetModel={}, prefix={}]",
|
||||
request.getTargetModel(), request.getPrefix(), ex);
|
||||
throw exception(VOICE_TTS_FAILED);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
package cn.iocoder.yudao.module.tik.voice.client.dto;
|
||||
|
||||
import lombok.Data;
|
||||
|
||||
/**
|
||||
* CosyVoice 语音复刻请求
|
||||
*/
|
||||
@Data
|
||||
public class CosyVoiceCloneRequest {
|
||||
|
||||
/**
|
||||
* 复刻模型(cosyvoice-v1 或 cosyvoice-v2)
|
||||
*/
|
||||
private String targetModel;
|
||||
|
||||
/**
|
||||
* 音色自定义前缀(仅允许数字和小写字母,长度<10字符)
|
||||
*/
|
||||
private String prefix;
|
||||
|
||||
/**
|
||||
* 音频文件公网URL
|
||||
*/
|
||||
private String url;
|
||||
|
||||
/**
|
||||
* 采样率,默认24000
|
||||
*/
|
||||
private Integer sampleRate;
|
||||
|
||||
/**
|
||||
* 音频格式,默认wav
|
||||
*/
|
||||
private String audioFormat;
|
||||
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
package cn.iocoder.yudao.module.tik.voice.client.dto;
|
||||
|
||||
import lombok.Data;
|
||||
|
||||
/**
|
||||
* CosyVoice 语音复刻结果
|
||||
*/
|
||||
@Data
|
||||
public class CosyVoiceCloneResult {
|
||||
|
||||
/**
|
||||
* 生成的 voice_id
|
||||
*/
|
||||
private String voiceId;
|
||||
|
||||
/**
|
||||
* 请求ID
|
||||
*/
|
||||
private String requestId;
|
||||
|
||||
}
|
||||
@@ -50,6 +50,11 @@ public class CosyVoiceProperties {
|
||||
*/
|
||||
private String ttsUrl = "https://dashscope.aliyuncs.com/api/v1/services/audio/tts/speech-synthesis";
|
||||
|
||||
/**
|
||||
* 语音复刻接口地址(声音注册)
|
||||
*/
|
||||
private String voiceEnrollmentUrl = "https://dashscope.aliyuncs.com/api/v1/services/audio/tts/voice-enrollment";
|
||||
|
||||
/**
|
||||
* 连接超时时间
|
||||
*/
|
||||
|
||||
@@ -54,6 +54,10 @@ public class TikUserVoiceDO extends TenantBaseDO {
|
||||
* 备注信息
|
||||
*/
|
||||
private String note;
|
||||
/**
|
||||
* 复刻音色ID(CosyVoice 语音复刻生成的 voice_id)
|
||||
*/
|
||||
private String voiceId;
|
||||
|
||||
}
|
||||
|
||||
|
||||
@@ -20,6 +20,8 @@ import cn.iocoder.yudao.module.tik.file.service.TikUserFileService;
|
||||
import cn.iocoder.yudao.module.tik.tikhup.service.TikHupService;
|
||||
import cn.iocoder.yudao.framework.mybatis.core.query.LambdaQueryWrapperX;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.CosyVoiceClient;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceCloneRequest;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceCloneResult;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceTtsRequest;
|
||||
import cn.iocoder.yudao.module.tik.voice.client.dto.CosyVoiceTtsResult;
|
||||
import cn.iocoder.yudao.module.tik.voice.config.CosyVoiceProperties;
|
||||
@@ -138,20 +140,30 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
|
||||
.setTranscription(null); // 初始为空,表示未识别
|
||||
voiceMapper.insert(voice);
|
||||
|
||||
// 4. 如果开启自动识别,异步执行识别(添加防重复检查)
|
||||
if (Boolean.TRUE.equals(createReqVO.getAutoTranscribe())) {
|
||||
// 再次检查是否已经有识别结果(防止并发重复创建)
|
||||
TikUserVoiceDO checkVoice = voiceMapper.selectById(voice.getId());
|
||||
if (StrUtil.isBlank(checkVoice.getTranscription())) {
|
||||
// 4. 调用阿里云语音复刻服务,生成 voice_id
|
||||
try {
|
||||
log.info("[createVoice][开始语音复刻,配音编号({}),文件ID({})]", voice.getId(), fileDO.getId());
|
||||
String fileAccessUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
|
||||
log.info("[createVoice][开启自动识别,配音编号({}),文件ID({}),预签名URL({})]",
|
||||
voice.getId(), fileDO.getId(), fileAccessUrl);
|
||||
asyncTranscribeVoice(voice.getId(), fileAccessUrl);
|
||||
} else {
|
||||
log.info("[createVoice][配音已经有识别结果,跳过自动识别,配音编号({})]", voice.getId());
|
||||
}
|
||||
|
||||
CosyVoiceCloneRequest cloneRequest = new CosyVoiceCloneRequest();
|
||||
cloneRequest.setTargetModel("cosyvoice-v2"); // 使用v2模型,效果更好
|
||||
cloneRequest.setPrefix("voice" + voice.getId()); // 音色前缀,格式要求
|
||||
cloneRequest.setUrl(fileAccessUrl);
|
||||
|
||||
CosyVoiceCloneResult cloneResult = cosyVoiceClient.cloneVoice(cloneRequest);
|
||||
String voiceId = cloneResult.getVoiceId();
|
||||
|
||||
// 更新配音记录,保存 voice_id
|
||||
voice.setVoiceId(voiceId);
|
||||
voiceMapper.updateById(voice);
|
||||
|
||||
log.info("[createVoice][语音复刻成功,配音编号({}),voice_id({})]", voice.getId(), voiceId);
|
||||
} catch (Exception e) {
|
||||
log.error("[createVoice][语音复刻失败,配音编号({}),错误信息: {}]", voice.getId(), e.getMessage(), e);
|
||||
// 复刻失败不影响配音记录创建,只记录日志
|
||||
}
|
||||
|
||||
|
||||
log.info("[createVoice][用户({})创建配音成功,配音编号({})]", userId, voice.getId());
|
||||
return voice.getId();
|
||||
}
|
||||
@@ -361,6 +373,13 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
|
||||
throw exception(VOICE_NOT_EXISTS, "配音不属于当前用户");
|
||||
}
|
||||
|
||||
// 优先使用复刻的 voice_id,如果不存在则使用文件URL(兼容旧数据)
|
||||
if (StrUtil.isNotBlank(voice.getVoiceId())) {
|
||||
log.info("[synthesizeVoice][使用复刻音色ID合成,配音编号({}),voice_id({})]", voiceConfigId, voice.getVoiceId());
|
||||
voiceId = voice.getVoiceId();
|
||||
transcriptionText = voice.getTranscription();
|
||||
} else {
|
||||
log.info("[synthesizeVoice][使用文件URL合成,配音编号({})]", voiceConfigId);
|
||||
// 获取文件信息,用于获取文件URL
|
||||
FileDO fileDO = fileMapper.selectById(voice.getFileId());
|
||||
if (fileDO == null) {
|
||||
@@ -374,6 +393,7 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
|
||||
throw exception(VOICE_NOT_EXISTS, "配音识别文本为空,请先进行语音识别");
|
||||
}
|
||||
}
|
||||
}
|
||||
// 2. 如果没有配置ID,使用voiceId或fileUrl(系统音色或直接URL方式)
|
||||
else {
|
||||
// 参数验证:如果使用fileUrl,建议提供transcriptionText以提高克隆质量
|
||||
@@ -513,6 +533,15 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
|
||||
throw exception(VOICE_NOT_EXISTS, "配音不属于当前用户");
|
||||
}
|
||||
|
||||
// 优先使用复刻的 voice_id,如果不存在则使用文件URL(兼容旧数据)
|
||||
if (StrUtil.isNotBlank(voice.getVoiceId())) {
|
||||
log.info("[previewVoice][使用复刻音色ID试听,配音编号({}),voice_id({})]", voiceConfigId, voice.getVoiceId());
|
||||
voiceId = voice.getVoiceId();
|
||||
transcriptionText = voice.getTranscription();
|
||||
inputText = StrUtil.blankToDefault(reqVO.getInputText(),
|
||||
StrUtil.blankToDefault(transcriptionText, cosyVoiceProperties.getPreviewText()));
|
||||
} else {
|
||||
log.info("[previewVoice][使用文件URL试听,配音编号({})]", voiceConfigId);
|
||||
// 获取文件信息,用于获取文件URL
|
||||
FileDO fileDO = fileMapper.selectById(voice.getFileId());
|
||||
if (fileDO == null) {
|
||||
@@ -528,6 +557,7 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
|
||||
inputText = StrUtil.blankToDefault(reqVO.getInputText(),
|
||||
StrUtil.blankToDefault(transcriptionText, cosyVoiceProperties.getPreviewText()));
|
||||
}
|
||||
}
|
||||
// 3. 如果没有配置ID,使用系统配音配置(需要前端传voiceId)
|
||||
else {
|
||||
log.info("[previewVoice][开始试听,使用系统配音配置,用户({})]", userId);
|
||||
|
||||
@@ -38,6 +38,9 @@ public class AppTikUserVoiceRespVO {
|
||||
@Schema(description = "备注", example = "这是一个测试配音")
|
||||
private String note;
|
||||
|
||||
@Schema(description = "复刻音色ID(CosyVoice 语音复刻生成的 voice_id)")
|
||||
private String voiceId;
|
||||
|
||||
@Schema(description = "创建时间", requiredMode = Schema.RequiredMode.REQUIRED)
|
||||
private LocalDateTime createTime;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user