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); + } + } + +} diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowProvider.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowProvider.java new file mode 100644 index 0000000000..2bf804b8bf --- /dev/null +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/SiliconFlowProvider.java @@ -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 + * + *
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); + } + } + +} diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowTtsRequest.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowTtsRequest.java new file mode 100644 index 0000000000..e60e1eaf09 --- /dev/null +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowTtsRequest.java @@ -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 + * + *
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; + +} diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadRequest.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadRequest.java new file mode 100644 index 0000000000..98ed68a419 --- /dev/null +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadRequest.java @@ -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 + * + *
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; + +} diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadResponse.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadResponse.java new file mode 100644 index 0000000000..6db6a521f4 --- /dev/null +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/SiliconFlowVoiceUploadResponse.java @@ -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; + +} diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/VoiceCloneRequest.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/VoiceCloneRequest.java index 1884ed3b62..5d3be6edf6 100644 --- a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/VoiceCloneRequest.java +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/VoiceCloneRequest.java @@ -48,4 +48,12 @@ public class VoiceCloneRequest { *
可选值: mp3, wav, flac
*/ private String audioFormat; + + /** + * 转录文本（可选） + * + *SiliconFlow: 音频对应的文本内容
+ *CosyVoice: 不适用
+ */ + private String transcriptionText; } diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/SiliconFlowProviderConfig.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/SiliconFlowProviderConfig.java new file mode 100644 index 0000000000..ac81e29c83 --- /dev/null +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/config/SiliconFlowProviderConfig.java @@ -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 + * + *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); + +} diff --git a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java index 0ba4723c9f..43c7a35a7e 100644 --- a/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java +++ b/yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java @@ -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 + } + } diff --git a/yudao-server/src/main/resources/application.yaml b/yudao-server/src/main/resources/application.yaml index 10e9f8e4c8..12f5a41874 100644 --- a/yudao-server/src/main/resources/application.yaml +++ b/yudao-server/src/main/resources/application.yaml @@ -220,6 +220,24 @@ yudao: sample-rate: 24000 audio-format: mp3 preview-text: 您好，欢迎体验专属音色 + voice: + default-provider: cosyvoice + providers: + cosyvoice: + enabled: true + api-key: sk-10c746f8cb8640738f8d6b71af699003 + default-model: cosyvoice-v3-flash + sample-rate: 24000 + audio-format: mp3 + preview-text: 您好，欢迎体验专属音色 + siliconflow: + enabled: false + api-key: sk-kcvifijrafkzxsmnxbgxspnxdvjiaawcbyoiqhmfobykynpx + base-url: https://api.siliconflow.cn + default-model: IndexTeam/IndexTTS-2 + sample-rate: 24000 + audio-format: mp3 + preview-text: 您好，欢迎体验专属音色 ai: gemini: # 谷歌 Gemini enable: true