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

代码优化

Browse Source
This commit is contained in:
sion123
2026-02-01 17:56:10 +08:00
parent 1d4c4465ac
commit 75bc7f2e47
16 changed files with 513 additions and 686 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/CosyVoiceClient.java
View File

@@ -7,7 +7,7 @@ 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 cn.iocoder.yudao.module.tik.voice.config.CosyVoiceProviderConfig;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesisParam;
import com.alibaba.dashscope.audio.ttsv2.SpeechSynthesizer;
import com.alibaba.dashscope.audio.ttsv2.enrollment.Voice;
@@ -45,7 +45,7 @@ public class CosyVoiceClient {
private static final MediaType JSON = MediaType.parse("application/json; charset=utf-8");
private final CosyVoiceProperties properties;
private final CosyVoiceProviderConfig config;
private final ObjectMapper objectMapper;
private volatile OkHttpClient httpClient;
@@ -54,7 +54,7 @@ public class CosyVoiceClient {
* 调用 CosyVoice TTS 接口
*/
public CosyVoiceTtsResult synthesize(CosyVoiceTtsRequest request) {
if (!properties.isEnabled()) {
if (!config.isEnabled()) {
throw exception0(VOICE_TTS_FAILED.getCode(), "未配置 CosyVoice API Key");
}
if (request == null || StrUtil.isBlank(request.getText())) {
@@ -69,15 +69,15 @@ public class CosyVoiceClient {
log.info("[CosyVoice][开始TTS][voiceId={}, textLength={}, model={}, speechRate={}, instruction={}]",
request.getVoiceId(),
request.getText().length(),
StrUtil.blankToDefault(request.getModel(), properties.getDefaultModel()),
StrUtil.blankToDefault(request.getModel(), config.getDefaultModel()),
request.getSpeechRate(),
request.getInstruction());
// 使用 DashScope SDK 构建参数（严格按文档）
// 注意：speechRate 和 volume 需要转换为 int 类型
SpeechSynthesisParam param = SpeechSynthesisParam.builder()
.apiKey(properties.getApiKey())
.model(StrUtil.blankToDefault(request.getModel(), properties.getDefaultModel()))
.apiKey(config.getApiKey())
.model(StrUtil.blankToDefault(request.getModel(), config.getDefaultModel()))
.voice(request.getVoiceId())
.speechRate(request.getSpeechRate() != null ? request.getSpeechRate().intValue() : 1)
.volume(request.getVolume() != null ? request.getVolume().intValue() : 0)
@@ -108,8 +108,8 @@ public class CosyVoiceClient {
// 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.setFormat(request.getAudioFormat() != null ? request.getAudioFormat() : config.getAudioFormat());
result.setSampleRate(request.getSampleRate() != null ? request.getSampleRate() : config.getSampleRate());
result.setRequestId(synthesizer.getLastRequestId());
result.setVoiceId(request.getVoiceId());
@@ -138,8 +138,8 @@ public class CosyVoiceClient {
private CosyVoiceTtsResult synthesizeViaHttp(CosyVoiceTtsRequest request) throws Exception {
String payload = objectMapper.writeValueAsString(buildPayload(request));
Request httpRequest = new Request.Builder()
.url(properties.getTtsUrl())
.addHeader("Authorization", "Bearer " + properties.getApiKey())
.url(config.getTtsUrl())
.addHeader("Authorization", "Bearer " + config.getApiKey())
.addHeader("Content-Type", "application/json")
.post(RequestBody.create(payload.getBytes(StandardCharsets.UTF_8), JSON))
.build();
@@ -158,7 +158,7 @@ public class CosyVoiceClient {
* 调用 CosyVoice 语音复刻接口（声音注册）
*/
public CosyVoiceCloneResult cloneVoice(CosyVoiceCloneRequest request) {
if (!properties.isEnabled()) {
if (!config.isEnabled()) {
throw exception0(VOICE_TTS_FAILED.getCode(), "未配置 CosyVoice API Key");
}
if (request == null || StrUtil.isBlank(request.getUrl())) {
@@ -176,7 +176,7 @@ public class CosyVoiceClient {
request.getTargetModel(), request.getPrefix(), request.getUrl());
// 使用 DashScope SDK 创建语音复刻
VoiceEnrollmentService service = new VoiceEnrollmentService(properties.getApiKey());
VoiceEnrollmentService service = new VoiceEnrollmentService(config.getApiKey());
Voice voice = service.createVoice(request.getTargetModel(), request.getPrefix(), request.getUrl());
log.info("[CosyVoice][语音复刻成功][Request ID: {}, Voice ID: {}]",
@@ -199,7 +199,7 @@ public class CosyVoiceClient {
private Map<String, Object> buildPayload(CosyVoiceTtsRequest request) {
Map<String, Object> payload = new HashMap<>();
String model = StrUtil.blankToDefault(request.getModel(), properties.getDefaultModel());
String model = StrUtil.blankToDefault(request.getModel(), config.getDefaultModel());
payload.put("model", model);
Map<String, Object> input = new HashMap<>();
@@ -218,7 +218,7 @@ public class CosyVoiceClient {
}
} else {
// 使用系统音色
String voiceId = StrUtil.blankToDefault(request.getVoiceId(), properties.getDefaultVoiceId());
String voiceId = StrUtil.blankToDefault(request.getVoiceId(), config.getDefaultVoiceId());
if (StrUtil.isNotBlank(voiceId)) {
input.put("voice", voiceId);
log.info("[CosyVoice][使用系统音色][voice={}]", voiceId);
@@ -229,11 +229,11 @@ public class CosyVoiceClient {
payload.put("input", input);
Map<String, Object> parameters = new HashMap<>();
int sampleRate = request.getSampleRate() != null ? request.getSampleRate() : properties.getSampleRate();
int sampleRate = request.getSampleRate() != null ? request.getSampleRate() : config.getSampleRate();
parameters.put("sample_rate", sampleRate);
// 根据官方文档，统一使用小写格式
String format = StrUtil.blankToDefault(request.getAudioFormat(), properties.getAudioFormat()).toLowerCase();
String format = StrUtil.blankToDefault(request.getAudioFormat(), config.getAudioFormat()).toLowerCase();
parameters.put("format", format);
if (request.getSpeechRate() != null) {
@@ -280,8 +280,8 @@ public class CosyVoiceClient {
byte[] audioBytes = Base64.getDecoder().decode(content);
CosyVoiceTtsResult result = new CosyVoiceTtsResult();
result.setAudio(audioBytes);
result.setFormat(firstAudio.path("format").asText(StrUtil.blankToDefault(request.getAudioFormat(), properties.getAudioFormat())));
result.setSampleRate(firstAudio.path("sample_rate").asInt(request.getSampleRate() != null ? request.getSampleRate() : properties.getSampleRate()));
result.setFormat(firstAudio.path("format").asText(StrUtil.blankToDefault(request.getAudioFormat(), config.getAudioFormat())));
result.setSampleRate(firstAudio.path("sample_rate").asInt(request.getSampleRate() != null ? request.getSampleRate() : config.getSampleRate()));
result.setRequestId(root.path("request_id").asText());
result.setVoiceId(firstAudio.path("voice").asText(request.getVoiceId()));
return result;
@@ -291,8 +291,8 @@ public class CosyVoiceClient {
if (httpClient == null) {
synchronized (this) {
if (httpClient == null) {
java.time.Duration connect = defaultDuration(properties.getConnectTimeout(), 10);
java.time.Duration read = defaultDuration(properties.getReadTimeout(), 60);
java.time.Duration connect = defaultDuration(config.getConnectTimeout(), 10);
java.time.Duration read = defaultDuration(config.getReadTimeout(), 60);
httpClient = new OkHttpClient.Builder()
.connectTimeout(connect.toMillis(), TimeUnit.MILLISECONDS)
.readTimeout(read.toMillis(), TimeUnit.MILLISECONDS)

43
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/CosyVoiceProvider.java
View File

@@ -1,11 +1,9 @@
package cn.iocoder.yudao.module.tik.voice.client;
import cn.hutool.core.util.StrUtil;
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.CosyVoiceProperties;
import cn.iocoder.yudao.module.tik.voice.config.CosyVoiceProviderConfig;
import cn.iocoder.yudao.module.tik.voice.config.VoiceProviderProperties;
import lombok.RequiredArgsConstructor;
@@ -26,56 +24,19 @@ import org.springframework.stereotype.Component;
public class CosyVoiceProvider implements VoiceCloneProvider {
private final CosyVoiceClient cosyVoiceClient;
/**
* 新配置（支持多供应商）
*/
private final VoiceProviderProperties voiceProviderProperties;
/**
* 旧配置（向后兼容）
*/
private final CosyVoiceProperties cosyVoiceProperties;
/**
* 获取 CosyVoice 配置
* 优先使用新配置，如果不存在则使用旧配置（向后兼容）
*/
private CosyVoiceProviderConfig getConfig() {
// 尝试从新配置获取
var baseConfig = voiceProviderProperties.getProviderConfig("cosyvoice");
if (baseConfig instanceof CosyVoiceProviderConfig cosyConfig) {
return cosyConfig;
if (baseConfig instanceof CosyVoiceProviderConfig config) {
return config;
}
// 回退到旧配置（向后兼容）
if (cosyVoiceProperties != null && cosyVoiceProperties.isEnabled()) {
return migrateFromLegacyConfig(cosyVoiceProperties);
}
// 返回空配置
return new CosyVoiceProviderConfig();
}
/**
* 从旧配置迁移到新配置格式
*/
private CosyVoiceProviderConfig migrateFromLegacyConfig(CosyVoiceProperties legacy) {
var config = new CosyVoiceProviderConfig();
config.setEnabled(true);
config.setApiKey(legacy.getApiKey());
config.setDefaultModel(legacy.getDefaultModel());
config.setDefaultVoiceId(legacy.getDefaultVoiceId());
config.setSampleRate(legacy.getSampleRate());
config.setAudioFormat(legacy.getAudioFormat());
config.setPreviewText(legacy.getPreviewText());
config.setTtsUrl(legacy.getTtsUrl());
config.setVoiceEnrollmentUrl(legacy.getVoiceEnrollmentUrl());
config.setConnectTimeout(legacy.getConnectTimeout());
config.setReadTimeout(legacy.getReadTimeout());
return config;
}
@Override
public VoiceCloneResult cloneVoice(VoiceCloneRequest request) {
log.info("[CosyVoiceProvider][语音克隆][audioUrl={}, model={}]",

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

@@ -1,123 +0,0 @@
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);
}
}
}

89
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowProvider.java
View File

@@ -1,6 +1,9 @@
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;
@@ -9,9 +12,9 @@ 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.http.MediaType;
import org.springframework.stereotype.Component;
import java.io.ByteArrayOutputStream;
@@ -23,7 +26,6 @@ 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
*/
@@ -35,29 +37,17 @@ 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();
}
private final SiliconFlowProviderConfig config;
@Override
public VoiceCloneResult cloneVoice(VoiceCloneRequest request) {
if (!config.isAvailable()) {
throw new RuntimeException("硅基流动供应商未配置或已禁用");
}
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);
@@ -68,7 +58,33 @@ public class SiliconFlowProvider implements VoiceCloneProvider {
sfRequest.setText(getOrDefault(request.getTranscriptionText(), config.getPreviewText()));
sfRequest.setAudio(AUDIO_MIME_TYPE + base64Audio);
SiliconFlowVoiceUploadResponse sfResponse = siliconFlowApi.uploadVoice(sfRequest);
// 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);
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("[SiliconFlowProvider][响应体]{}", responseBody);
if (!response.isOk()) {
log.error("[SiliconFlowProvider][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 sfResponse = JSONUtil.toBean(responseBody,
SiliconFlowVoiceUploadResponse.class);
if (StrUtil.isBlank(sfResponse.getUri())) {
throw new RuntimeException("硅基流动上传参考音频失败: 响应中缺少 uri");
}
VoiceCloneResult result = new VoiceCloneResult();
result.setVoiceId(sfResponse.getUri());
@@ -89,13 +105,15 @@ public class SiliconFlowProvider implements VoiceCloneProvider {
@Override
public VoiceTtsResult synthesize(VoiceTtsRequest request) {
if (!config.isAvailable()) {
throw new RuntimeException("硅基流动供应商未配置或已禁用");
}
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()))
@@ -106,16 +124,37 @@ public class SiliconFlowProvider implements VoiceCloneProvider {
.responseFormat(getOrDefault(request.getAudioFormat(), config.getAudioFormat()))
.build();
String base64Audio = siliconFlowApi.synthesize(sfRequest);
// 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);
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("[SiliconFlowProvider][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 = Base64.getEncoder().encodeToString(audioBytes);
VoiceTtsResult result = new VoiceTtsResult();
result.setAudio(base64Audio);
result.setAudio(Base64.getDecoder().decode(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);
result.getFormat(), result.getAudio() != null ? result.getAudio().length : 0);
return result;
} catch (Exception e) {

79
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/CosyVoiceProperties.java
View File

@@ -1,79 +0,0 @@
package cn.iocoder.yudao.module.tik.voice.config;
import cn.hutool.core.util.StrUtil;
import lombok.Data;
import org.springframework.boot.context.properties.ConfigurationProperties;
import org.springframework.stereotype.Component;
import java.time.Duration;
/**
* CosyVoice 配置
*/
@Data
@Component
@ConfigurationProperties(prefix = "yudao.cosyvoice")
public class CosyVoiceProperties {
/**
* DashScope API Key
*/
private String apiKey;
/**
* 默认模型
*/
private String defaultModel = "cosyvoice-v3-flash";
/**
* 默认 voiceId（可选）
*/
private String defaultVoiceId;
/**
* 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 = "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
*/
private Duration connectTimeout = Duration.ofSeconds(10);
/**
* 读取超时时间（改为3分钟，提升语音合成成功率）
*/
private Duration readTimeout = Duration.ofSeconds(180);
/**
* 是否启用
*/
private boolean enabled = true;
public boolean isEnabled() {
return enabled && StrUtil.isNotBlank(apiKey);
}
}

11
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/SiliconFlowProviderConfig.java
View File

@@ -2,6 +2,8 @@ package cn.iocoder.yudao.module.tik.voice.config;
import lombok.Data;
import lombok.EqualsAndHashCode;
import org.springframework.boot.context.properties.ConfigurationProperties;
import org.springframework.stereotype.Component;
import java.time.Duration;
@@ -14,6 +16,8 @@ import java.time.Duration;
*/
@Data
@EqualsAndHashCode(callSuper = true)
@Component
@ConfigurationProperties(prefix = "yudao.voice.siliconflow")
public class SiliconFlowProviderConfig extends VoiceProviderProperties.ProviderConfig {
/**
@@ -61,4 +65,11 @@ public class SiliconFlowProviderConfig extends VoiceProviderProperties.ProviderC
*/
private Duration readTimeout = Duration.ofSeconds(180);
/**
* 检查是否可用（有 API Key 即可用）
*/
public boolean isAvailable() {
return isEnabled() && getApiKey() != null && !getApiKey().isEmpty();
}
}

23
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java
View File

@@ -25,7 +25,6 @@ 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.CosyVoiceProperties;
import cn.iocoder.yudao.module.tik.voice.config.VoiceProviderProperties;
import cn.iocoder.yudao.module.tik.voice.dal.dataobject.TikUserVoiceDO;
import cn.iocoder.yudao.module.tik.voice.dal.mysql.TikUserVoiceMapper;
@@ -88,9 +87,6 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
@Resource
private VoiceCloneProviderFactory voiceProviderFactory;
@Resource
private CosyVoiceProperties cosyVoiceProperties;
@Resource
private VoiceProviderProperties voiceProviderProperties;
@@ -649,8 +645,7 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
}
/**
* 获取 CosyVoice 配置（统一入口）
* 优先使用新配置，回退到旧配置
* 获取 CosyVoice 配置
*/
private cn.iocoder.yudao.module.tik.voice.config.CosyVoiceProviderConfig getCosyVoiceConfig() {
if (voiceProviderProperties != null) {
@@ -664,31 +659,23 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
/**
* 获取默认音频格式
* 优先使用新配置，回退到旧配置
*/
private String getDefaultFormat() {
var config = getCosyVoiceConfig();
if (config != null) {
return config.getAudioFormat();
}
if (cosyVoiceProperties != null) {
return cosyVoiceProperties.getAudioFormat();
}
return "mp3";
}
/**
* 获取默认采样率
* 优先使用新配置，回退到旧配置
*/
private Integer getDefaultSampleRate() {
var config = getCosyVoiceConfig();
if (config != null) {
return config.getSampleRate();
}
if (cosyVoiceProperties != null) {
return cosyVoiceProperties.getSampleRate();
}
return 24000;
}
@@ -1173,31 +1160,23 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
/**
* 获取默认音色ID
* 优先使用新配置，回退到旧配置
*/
private String getDefaultVoiceId() {
var config = getCosyVoiceConfig();
if (config != null) {
return config.getDefaultVoiceId();
}
if (cosyVoiceProperties != null) {
return cosyVoiceProperties.getDefaultVoiceId();
}
return null;
}
/**
* 获取试听文本
* 优先使用新配置，回退到旧配置
*/
private String getPreviewText() {
var config = getCosyVoiceConfig();
if (config != null) {
return config.getPreviewText();
}
if (cosyVoiceProperties != null) {
return cosyVoiceProperties.getPreviewText();
}
return "您好，欢迎体验专属音色。";
}