sion/sionrui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix:问题

Browse Source
This commit is contained in:
sion123
2026-02-02 02:39:40 +08:00
parent 49c660a6e3
commit 33b748915d
9 changed files with 96 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowProvider.java
View File

@@ -58,7 +58,6 @@ public class SiliconFlowProvider implements VoiceCloneProvider {
sfRequest.setText(getOrDefault(request.getTranscriptionText(), config.getPreviewText()));
sfRequest.setAudio(AUDIO_MIME_TYPE + base64Audio);
// 调用上传参考音频 API
String url = config.getBaseUrl() + config.getVoiceUploadUrl();
String requestBody = JSONUtil.toJsonStr(sfRequest);
log.debug("[SiliconFlowProvider][请求体]{}", requestBody);
@@ -123,7 +122,6 @@ public class SiliconFlowProvider implements VoiceCloneProvider {
.responseFormat(getOrDefault(request.getAudioFormat(), config.getAudioFormat()))
.build();
// 调用文本转语音 API
String url = config.getBaseUrl() + config.getTtsUrl();
String requestBody = JSONUtil.toJsonStr(sfRequest);
log.debug("[SiliconFlowProvider][请求体]{}", requestBody);
@@ -142,7 +140,6 @@ public class SiliconFlowProvider implements VoiceCloneProvider {
throw new RuntimeException("硅基流动文本转语音失败: " + errorBody);
}
// 硅基流动直接返回二进制音频数据
byte[] audioBytes = response.bodyBytes();
String base64Audio = Base64.getEncoder().encodeToString(audioBytes);

2
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowTtsRequest.java
View File

@@ -36,8 +36,6 @@ public class SiliconFlowTtsRequest {
*/
private Float speed;
/**
* 响应格式（mp3, opus, wav, pcm）（API 参数名：response_format）
*/

5
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/SiliconFlowProviderConfig.java
View File

@@ -32,8 +32,11 @@ public class SiliconFlowProviderConfig extends VoiceProviderProperties.ProviderC
/**
* 默认采样率
* <p>mp3: 32000, 44100 (默认 44100)</p>
* <p>opus: 48000</p>
* <p>wav/pcm: 8000, 16000, 24000, 32000, 44100 (默认 44100)</p>
*/
private Integer sampleRate = 24000;
private Integer sampleRate = 44100;
/**
* 默认音频格式

44
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java
View File

@@ -144,34 +144,38 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
.setLanguage(StrUtil.blankToDefault(createReqVO.getLanguage(), "zh-CN"))
.setGender(StrUtil.blankToDefault(createReqVO.getGender(), "female"))
.setNote(createReqVO.getNote())
.setTranscription(null); // 初始为空，表示未识别
.setTranscription(createReqVO.getText()); // 使用前端传入的文本
voiceMapper.insert(voice);
// 4. 调用语音克隆服务，生成 voice_id
try {
log.info("[createVoice][开始语音复刻，配音编号({})，文件ID({})，供应商({})]",
voice.getId(), fileDO.getId(), createReqVO.getProviderType());
String fileAccessUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
if (StrUtil.isNotBlank(createReqVO.getText())) {
try {
log.info("[createVoice][开始语音复刻，配音编号({})，文件ID({})，供应商({})]",
voice.getId(), fileDO.getId(), createReqVO.getProviderType());
String fileAccessUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
VoiceCloneProvider provider = voiceProviderFactory.getProvider(createReqVO.getProviderType());
String providerType = getProviderType(createReqVO.getProviderType(), provider);
String model = getModelByProvider(providerType);
VoiceCloneProvider provider = voiceProviderFactory.getProvider(createReqVO.getProviderType());
String providerType = getProviderType(createReqVO.getProviderType(), provider);
String model = getModelByProvider(providerType);
VoiceCloneRequest cloneRequest = new VoiceCloneRequest();
cloneRequest.setAudioUrl(fileAccessUrl);
cloneRequest.setModel(model);
cloneRequest.setPrefix("voice" + voice.getId());
cloneRequest.setTranscriptionText(voice.getTranscription());
VoiceCloneRequest cloneRequest = new VoiceCloneRequest();
cloneRequest.setAudioUrl(fileAccessUrl);
cloneRequest.setModel(model);
cloneRequest.setPrefix("voice" + voice.getId());
cloneRequest.setTranscriptionText(createReqVO.getText()); // 使用前端传入的文本
VoiceCloneResult cloneResult = provider.cloneVoice(cloneRequest);
String voiceId = cloneResult.getVoiceId();
VoiceCloneResult cloneResult = provider.cloneVoice(cloneRequest);
String voiceId = cloneResult.getVoiceId();
voice.setVoiceId(voiceId);
voiceMapper.updateById(voice);
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);
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);
}
} else {
log.info("[createVoice][未提供文本，跳过语音复刻，配音编号({})]", voice.getId());
}

5
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/vo/AppTikUserVoiceCreateReqVO.java
View File

@@ -3,6 +3,7 @@ package cn.iocoder.yudao.module.tik.voice.vo;
import io.swagger.v3.oas.annotations.media.Schema;
import jakarta.validation.constraints.NotBlank;
import jakarta.validation.constraints.NotNull;
import jakarta.validation.constraints.Size;
import lombok.Data;
/**
@@ -34,6 +35,10 @@ public class AppTikUserVoiceCreateReqVO {
@Schema(description = "备注", example = "这是一个测试配音")
private String note;
@Schema(description = "音频文本（用于语音复刻，前端通过音频识别获取）")
@Size(max = 4000, message = "音频文本不能超过 4000 个字符")
private String text;
@Schema(description = "供应商类型：cosyvoice-阿里云，siliconflow-硅基流动（不传则使用默认）", example = "cosyvoice")
private String providerType;