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

增加轨迹流动

Browse Source
This commit is contained in:
sion123
2026-02-01 17:32:31 +08:00
parent 24f66c8e81
commit 97b1fe9a53
9 changed files with 506 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowApi.java Normal file
View File

@@ -0,0 +1,123 @@
package cn.iocoder.yudao.module.tik.voice.client;
import cn.hutool.core.util.StrUtil;
import cn.hutool.http.HttpRequest;
import cn.hutool.http.HttpResponse;
import cn.hutool.json.JSONUtil;
import cn.iocoder.yudao.module.tik.voice.client.dto.SiliconFlowTtsRequest;
import cn.iocoder.yudao.module.tik.voice.client.dto.SiliconFlowVoiceUploadRequest;
import cn.iocoder.yudao.module.tik.voice.client.dto.SiliconFlowVoiceUploadResponse;
import cn.iocoder.yudao.module.tik.voice.config.SiliconFlowProviderConfig;
import lombok.RequiredArgsConstructor;
import lombok.extern.slf4j.Slf4j;
import org.springframework.http.MediaType;
import org.springframework.stereotype.Component;
/**
* 硅基流动 API 客户端
*
* <p>提供硅基流动语音服务的 HTTP 调用能力。
*
* @author 芋道源码
*/
@Slf4j
@Component
@RequiredArgsConstructor
public class SiliconFlowApi {
private final SiliconFlowProviderConfig config;
/**
* 上传参考音频（语音克隆）
*
* @param request 上传请求
* @return 上传响应，包含音色 URI
*/
public SiliconFlowVoiceUploadResponse uploadVoice(SiliconFlowVoiceUploadRequest request) {
String url = config.getBaseUrl() + config.getVoiceUploadUrl();
log.info("[SiliconFlowApi][上传参考音频][url={}, model={}, customName={}]",
url, request.getModel(), request.getCustomName());
try {
String requestBody = JSONUtil.toJsonStr(request);
log.debug("[SiliconFlowApi][请求体]{}", requestBody);
HttpResponse response = HttpRequest.post(url)
.header("Authorization", "Bearer " + config.getApiKey())
.header("Content-Type", MediaType.APPLICATION_JSON_VALUE)
.body(requestBody)
.timeout((int) config.getConnectTimeout().toMillis())
.execute();
String responseBody = response.body();
log.debug("[SiliconFlowApi][响应体]{}", responseBody);
if (!response.isOk()) {
log.error("[SiliconFlowApi][上传失败][code={}, body={}]",
response.getStatus(), responseBody);
throw new RuntimeException("硅基流动上传参考音频失败: " + responseBody);
}
SiliconFlowVoiceUploadResponse result = JSONUtil.toBean(responseBody,
SiliconFlowVoiceUploadResponse.class);
if (StrUtil.isBlank(result.getUri())) {
throw new RuntimeException("硅基流动上传参考音频失败: 响应中缺少 uri");
}
log.info("[SiliconFlowApi][上传成功][uri={}]", result.getUri());
return result;
} catch (Exception e) {
log.error("[SiliconFlowApi][上传异常]", e);
throw new RuntimeException("硅基流动上传参考音频异常: " + e.getMessage(), e);
}
}
/**
* 文本转语音
*
* @param request TTS 请求
* @return 音频数据（base64 编码）
*/
public String synthesize(SiliconFlowTtsRequest request) {
String url = config.getBaseUrl() + config.getTtsUrl();
log.info("[SiliconFlowApi][文本转语音][url={}, model={}, inputLength={}]",
url, request.getModel(),
request.getInput() != null ? request.getInput().length() : 0);
try {
String requestBody = JSONUtil.toJsonStr(request);
log.debug("[SiliconFlowApi][请求体]{}", requestBody);
HttpResponse response = HttpRequest.post(url)
.header("Authorization", "Bearer " + config.getApiKey())
.header("Content-Type", MediaType.APPLICATION_JSON_VALUE)
.body(requestBody)
.timeout((int) config.getReadTimeout().toMillis())
.execute();
if (!response.isOk()) {
String errorBody = response.body();
log.error("[SiliconFlowApi][合成失败][code={}, body={}]",
response.getStatus(), errorBody);
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 = java.util.Base64.getEncoder().encodeToString(audioBytes);
log.info("[SiliconFlowApi][合成成功][format={}, size={}]",
request.getResponseFormat(), audioBytes.length);
return base64Audio;
} catch (Exception e) {
log.error("[SiliconFlowApi][合成异常]", e);
throw new RuntimeException("硅基流动文本转语音异常: " + e.getMessage(), e);
}
}
}

159
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowProvider.java Normal file
View File

@@ -0,0 +1,159 @@
package cn.iocoder.yudao.module.tik.voice.client;
import cn.hutool.core.util.StrUtil;
import cn.iocoder.yudao.module.tik.voice.client.dto.SiliconFlowTtsRequest;
import cn.iocoder.yudao.module.tik.voice.client.dto.SiliconFlowVoiceUploadRequest;
import cn.iocoder.yudao.module.tik.voice.client.dto.SiliconFlowVoiceUploadResponse;
import cn.iocoder.yudao.module.tik.voice.client.dto.VoiceCloneRequest;
import cn.iocoder.yudao.module.tik.voice.client.dto.VoiceCloneResult;
import cn.iocoder.yudao.module.tik.voice.client.dto.VoiceTtsRequest;
import cn.iocoder.yudao.module.tik.voice.client.dto.VoiceTtsResult;
import cn.iocoder.yudao.module.tik.voice.config.SiliconFlowProviderConfig;
import cn.iocoder.yudao.module.tik.voice.config.VoiceProviderProperties;
import lombok.RequiredArgsConstructor;
import lombok.extern.slf4j.Slf4j;
import org.springframework.stereotype.Component;
import java.io.ByteArrayOutputStream;
import java.io.InputStream;
import java.net.URL;
import java.util.Base64;
/**
* 硅基流动 Provider 实现
*
* <p>硅基流动语音服务的 Provider 实现。
* 内部委托给 {@link SiliconFlowApi} 进行实际的API调用。
*
* @author 芋道源码
*/
@Slf4j
@Component
@RequiredArgsConstructor
public class SiliconFlowProvider implements VoiceCloneProvider {
private static final String PROVIDER_TYPE = "siliconflow";
private static final String AUDIO_MIME_TYPE = "data:audio/mpeg;base64,";
private final SiliconFlowApi siliconFlowApi;
private final VoiceProviderProperties voiceProviderProperties;
/**
* 获取硅基流动配置
*/
private SiliconFlowProviderConfig getConfig() {
var baseConfig = voiceProviderProperties.getProviderConfig("siliconflow");
if (baseConfig instanceof SiliconFlowProviderConfig config) {
return config;
}
// 返回默认配置
return new SiliconFlowProviderConfig();
}
@Override
public VoiceCloneResult cloneVoice(VoiceCloneRequest request) {
log.info("[SiliconFlowProvider][语音克隆][audioUrl={}, model={}]",
request.getAudioUrl(), request.getModel());
SiliconFlowProviderConfig config = getConfig();
try {
byte[] audioData = downloadAudio(request.getAudioUrl());
String base64Audio = Base64.getEncoder().encodeToString(audioData);
SiliconFlowVoiceUploadRequest sfRequest = new SiliconFlowVoiceUploadRequest();
sfRequest.setModel(getOrDefault(request.getModel(), config.getDefaultModel()));
sfRequest.setCustomName(getOrDefault(request.getPrefix(), "voice_" + System.currentTimeMillis()));
sfRequest.setText(getOrDefault(request.getTranscriptionText(), config.getPreviewText()));
sfRequest.setAudio(AUDIO_MIME_TYPE + base64Audio);
SiliconFlowVoiceUploadResponse sfResponse = siliconFlowApi.uploadVoice(sfRequest);
VoiceCloneResult result = new VoiceCloneResult();
result.setVoiceId(sfResponse.getUri());
result.setRequestId(sfResponse.getUri());
log.info("[SiliconFlowProvider][语音克隆成功][voiceId={}]", result.getVoiceId());
return result;
} catch (Exception e) {
log.error("[SiliconFlowProvider][语音克隆失败]", e);
throw new RuntimeException("硅基流动语音克隆失败: " + e.getMessage(), e);
}
}
private String getOrDefault(String value, String defaultValue) {
return StrUtil.isNotBlank(value) ? value : defaultValue;
}
@Override
public VoiceTtsResult synthesize(VoiceTtsRequest request) {
log.info("[SiliconFlowProvider][语音合成][voiceId={}, textLength={}, model={}]",
request.getVoiceId(),
request.getText() != null ? request.getText().length() : 0,
request.getModel());
SiliconFlowProviderConfig config = getConfig();
try {
SiliconFlowTtsRequest sfRequest = SiliconFlowTtsRequest.builder()
.model(getOrDefault(request.getModel(), config.getDefaultModel()))
.input(request.getText())
.voice(request.getVoiceId())
.speed(request.getSpeechRate() != null ? request.getSpeechRate() : 1.0f)
.sampleRate(request.getSampleRate() != null ? request.getSampleRate() : config.getSampleRate())
.responseFormat(getOrDefault(request.getAudioFormat(), config.getAudioFormat()))
.build();
String base64Audio = siliconFlowApi.synthesize(sfRequest);
VoiceTtsResult result = new VoiceTtsResult();
result.setAudio(base64Audio);
result.setFormat(sfRequest.getResponseFormat());
result.setSampleRate(sfRequest.getSampleRate());
result.setVoiceId(request.getVoiceId());
log.info("[SiliconFlowProvider][语音合成成功][format={}, audioSize={}]",
result.getFormat(), base64Audio != null ? base64Audio.length() : 0);
return result;
} catch (Exception e) {
log.error("[SiliconFlowProvider][语音合成失败]", e);
throw new RuntimeException("硅基流动语音合成失败: " + e.getMessage(), e);
}
}
@Override
public boolean supports(String providerType) {
return PROVIDER_TYPE.equalsIgnoreCase(providerType);
}
@Override
public String getProviderType() {
return PROVIDER_TYPE;
}
private byte[] downloadAudio(String audioUrl) {
log.info("[SiliconFlowProvider][下载音频][url={}]", audioUrl);
try {
URL url = new URL(audioUrl);
try (InputStream in = url.openStream();
ByteArrayOutputStream out = new ByteArrayOutputStream()) {
byte[] buffer = new byte[8192];
int bytesRead;
while ((bytesRead = in.read(buffer)) != -1) {
out.write(buffer, 0, bytesRead);
}
byte[] result = out.toByteArray();
log.info("[SiliconFlowProvider][下载成功][size={}]", result.length);
return result;
}
} catch (Exception e) {
log.error("[SiliconFlowProvider][下载失败]", e);
throw new RuntimeException("下载音频文件失败: " + e.getMessage(), e);
}
}
}

47
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowTtsRequest.java Normal file
View File

@@ -0,0 +1,47 @@
package cn.iocoder.yudao.module.tik.voice.client.dto;
import lombok.Builder;
import lombok.Data;
/**
* 硅基流动文本转语音请求
*
* <p>对应 API: POST /v1/audio/speech
*
* @author 芋道源码
*/
@Data
@Builder
public class SiliconFlowTtsRequest {
/**
* 模型名称
*/
private String model;
/**
* 待合成文本
*/
private String input;
/**
* 音色 ID（使用上传参考音频返回的 uri）
*/
private String voice;
/**
* 语速（0.25 - 4.0，默认 1.0）
*/
private Float speed;
/**
* 采样率（如 24000）
*/
private Integer sampleRate;
/**
* 响应格式（mp3, wav, pcm）
*/
private String responseFormat;
}

35
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadRequest.java Normal file
View File

@@ -0,0 +1,35 @@
package cn.iocoder.yudao.module.tik.voice.client.dto;
import lombok.Data;
/**
* 硅基流动上传参考音频请求
*
* <p>对应 API: POST /v1/uploads/audio/voice
*
* @author 芋道源码
*/
@Data
public class SiliconFlowVoiceUploadRequest {
/**
* 模型名称
*/
private String model;
/**
* 用户自定义音色名称
*/
private String customName;
/**
* 音频对应的文本内容
*/
private String text;
/**
* 音频数据（base64 编码，格式：data:audio/mpeg;base64,xxx）
*/
private String audio;
}

18
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadResponse.java Normal file
View File

@@ -0,0 +1,18 @@
package cn.iocoder.yudao.module.tik.voice.client.dto;
import lombok.Data;
/**
* 硅基流动上传参考音频响应
*
* @author 芋道源码
*/
@Data
public class SiliconFlowVoiceUploadResponse {
/**
* 音色 URI（格式：speech:customName:xxx:xxx）
*/
private String uri;
}

8
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/VoiceCloneRequest.java
View File

@@ -48,4 +48,12 @@ public class VoiceCloneRequest {
* <p>可选值: mp3, wav, flac</p>
*/
private String audioFormat;
/**
* 转录文本（可选）
*
* <p>SiliconFlow: 音频对应的文本内容</p>
* <p>CosyVoice: 不适用</p>
*/
private String transcriptionText;
}

64
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/SiliconFlowProviderConfig.java Normal file
View File

@@ -0,0 +1,64 @@
package cn.iocoder.yudao.module.tik.voice.config;
import lombok.Data;
import lombok.EqualsAndHashCode;
import java.time.Duration;
/**
* 硅基流动供应商配置
*
* <p>继承通用配置，添加硅基流动特有字段。
*
* @author 芋道源码
*/
@Data
@EqualsAndHashCode(callSuper = true)
public class SiliconFlowProviderConfig extends VoiceProviderProperties.ProviderConfig {
/**
* API 基础 URL
*/
private String baseUrl = "https://api.siliconflow.cn";
/**
* 默认模型
*/
private String defaultModel = "IndexTeam/IndexTTS-2";
/**
* 默认采样率
*/
private Integer sampleRate = 24000;
/**
* 默认音频格式
*/
private String audioFormat = "mp3";
/**
* 试听默认示例文本
*/
private String previewText = "您好，欢迎体验专属音色。";
/**
* TTS 接口地址
*/
private String ttsUrl = "/v1/audio/speech";
/**
* 语音复刻接口地址（上传参考音频）
*/
private String voiceUploadUrl = "/v1/uploads/audio/voice";
/**
* 连接超时时间
*/
private Duration connectTimeout = Duration.ofSeconds(10);
/**
* 读取超时时间（3分钟，提升语音合成成功率）
*/
private Duration readTimeout = Duration.ofSeconds(180);
}

39
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java
View File

@@ -104,6 +104,14 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
private static final long PREVIEW_CACHE_TTL_SECONDS = 3600;
private static final long SYNTH_CACHE_TTL_SECONDS = 24 * 3600;
/** 供应商类型常量 */
private static final String PROVIDER_COSYVOICE = "cosyvoice";
private static final String PROVIDER_SILICONFLOW = "siliconflow";
/** 模型常量 */
private static final String MODEL_COSYVOICE = "cosyvoice-v3-flash";
private static final String MODEL_SILICONFLOW = "IndexTeam/IndexTTS-2";
@Override
@Transactional(rollbackFor = Exception.class)
public Long createVoice(AppTikUserVoiceCreateReqVO createReqVO) {
@@ -150,24 +158,25 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
voice.getId(), fileDO.getId(), createReqVO.getProviderType());
String fileAccessUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
// 使用 Provider 接口（支持前端选择供应商，不传则使用默认）
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("cosyvoice-v3-flash"); // 使用v3-flash模型
cloneRequest.setPrefix("voice" + voice.getId()); // 音色前缀，格式要求
cloneRequest.setModel(model);
cloneRequest.setPrefix("voice" + voice.getId());
cloneRequest.setTranscriptionText(voice.getTranscription());
VoiceCloneResult cloneResult = provider.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
}
@@ -1192,5 +1201,25 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
return "您好，欢迎体验专属音色。";
}
/**
* 获取供应商类型
*/
private String getProviderType(String requestProviderType, VoiceCloneProvider provider) {
if (StrUtil.isNotBlank(requestProviderType)) {
return requestProviderType;
}
return provider.getProviderType();
}
/**
* 根据供应商类型获取对应的模型
*/
private String getModelByProvider(String providerType) {
if (PROVIDER_SILICONFLOW.equalsIgnoreCase(providerType)) {
return MODEL_SILICONFLOW;
}
return MODEL_COSYVOICE; // 默认使用 CosyVoice 模型
}
}