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

优化

Browse Source
This commit is contained in:
sion123
2025-11-19 01:39:56 +08:00
parent cc8e503f49
commit f052b0af65
11 changed files with 956 additions and 1124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
frontend/app/web-gold/src/api/userPrompt.js
View File

@@ -15,7 +15,12 @@ export const UserPromptApi = {
* @returns {Promise} 响应数据
*/
createUserPrompt: async (data) => {
return await http.post(`${SERVER_BASE_AI}/user-prompt/create`, data)
console.log('[UserPromptApi] 发送请求参数:', JSON.stringify(data, null, 2))
return await http.post(`${SERVER_BASE_AI}/user-prompt/create`, data, {
headers: {
'Content-Type': 'application/json'
}
})
},
/**

14
frontend/app/web-gold/src/views/content-style/components/SavePromptModal.vue
View File

@@ -54,17 +54,27 @@ async function handleSave() {
savingPrompt.value = true
try {
// 确保 content 字段有值
const content = savePromptForm.value.content?.trim() || ''
if (!content) {
message.error('提示词内容不能为空')
savingPrompt.value = false
return
}
const payload = {
userId: userId,
name: savePromptForm.value.name.trim(),
content: savePromptForm.value.content.trim(),
category: savePromptForm.value.category.trim() || null,
content: content, // 确保 content 有值
category: savePromptForm.value.category?.trim() || null,
isPublic: false,
sort: 0,
useCount: 0,
status: 1,
}
console.log('[SavePromptModal] 发送请求参数:', payload)
const response = await UserPromptApi.createUserPrompt(payload)
if (response && (response.code === 0 || response.code === 200)) {

1197
frontend/app/web-gold/src/views/dh/Video.vue
View File

File diff suppressed because it is too large Load Diff

332
frontend/app/web-gold/src/views/dh/VoiceCopy.vue
View File

@@ -2,12 +2,10 @@
<div class="voice-copy-page">
<!-- 页面头部 -->
<div class="page-header">
<h1 class="page-title">配音管理</h1>
<h1>配音管理</h1>
<a-button type="primary" @click="handleCreate">
<template #icon>
<PlusOutlined />
</template>
<span>新建配音</span>
<PlusOutlined />
新建配音
</a-button>
</div>
@@ -18,12 +16,9 @@
v-model:value="searchParams.name"
placeholder="搜索配音名称"
style="width: 250px"
allow-clear
@press-enter="handleSearch"
>
<template #prefix>
<SearchOutlined />
</template>
<SearchOutlined />
</a-input>
<a-button type="primary" @click="handleSearch">查询</a-button>
<a-button @click="handleReset">重置</a-button>
@@ -41,43 +36,37 @@
@change="handleTableChange"
>
<template #bodyCell="{ column, record }">
<template v-if="column.key === 'name'">
<div class="voice-name">{{ record.name || '未命名' }}</div>
</template>
<template v-else-if="column.key === 'transcription'">
<div class="transcription-text">{{ formatTranscription(record.transcription) }}</div>
</template>
<template v-else-if="column.key === 'createTime'">
<span>{{ formatDateTime(record.createTime) }}</span>
</template>
<template v-else-if="column.key === 'fileUrl'">
<a-button type="link" size="small" @click="handlePlayAudio(record)">
<template #icon>
<PlayCircleOutlined />
</template>
播放
<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>
<a-button v-else-if="column.key === 'fileUrl'" type="link" size="small" @click="handlePlayAudio(record)">
<PlayCircleOutlined />
播放
</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>
</template>
<template v-else-if="column.key === 'actions'">
<a-space>
<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>
<a-button type="link" size="small" danger @click="handleDelete(record)">删除</a-button>
</a-space>
</template>
</a-table>
</div>
<!-- 新建/编辑表单 Modal -->
<!-- 表单 Modal -->
<a-modal
v-model:open="modalVisible"
:title="isCreateMode ? '新建配音' : '编辑配音'"
@@ -86,12 +75,7 @@
@ok="handleSubmit"
@cancel="handleCancel"
>
<a-form
ref="formRef"
:model="formData"
:rules="formRules"
layout="vertical"
>
<a-form ref="formRef" :model="formData" :rules="formRules" layout="vertical">
<a-form-item label="配音名称" name="name">
<a-input v-model:value="formData.name" placeholder="请输入配音名称" />
</a-form-item>
@@ -106,37 +90,29 @@
v-model:file-list="fileList"
:custom-request="handleCustomUpload"
:before-upload="handleBeforeUpload"
:show-upload-list="true"
:max-count="1"
accept="audio/*,.mp3,.wav,.aac,.m4a,.flac,.ogg"
@remove="handleRemoveFile"
@change="handleFileListChange"
>
<a-button type="primary" :loading="uploading">
<template #icon>
<UploadOutlined v-if="!uploading" />
</template>
<UploadOutlined v-if="!uploading" />
{{ uploading ? '上传中...' : (fileList.length > 0 ? '重新上传' : '上传音频文件') }}
</a-button>
</a-upload>
<div class="upload-hint">支持格式：MP3、WAV、AAC、M4A、FLAC、OGG，单个文件不超过 100MB</div>
<div class="upload-hint">
支持格式：MP3、WAV、AAC、M4A、FLAC、OGG，单个文件不超过 50MB<br>
<span class="hint-text">🎤 配音建议：使用 30 秒 - 2 分钟的短配音效果更佳</span>
</div>
</a-form-item>
<a-form-item label="备注" name="note">
<a-textarea
v-model:value="formData.note"
:rows="3"
placeholder="请输入备注信息"
/>
<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-form-item v-if="!isCreateMode" label="识别内容" name="transcription">
<a-textarea
v-model:value="formData.transcription"
v-model="formData.transcription"
:rows="4"
placeholder="识别内容，支持手动修改"
/>
@@ -144,29 +120,23 @@
</a-form>
</a-modal>
<!-- 音频播放器 -->
<audio ref="audioPlayer" style="display: none" controls />
<audio ref="audioPlayer" style="display: none" />
</div>
</template>
<script setup>
import { ref, reactive, computed, onMounted, onUnmounted, nextTick } from 'vue'
import { message, Modal } from 'ant-design-vue'
import {
PlusOutlined,
SearchOutlined,
UploadOutlined,
PlayCircleOutlined
} from '@ant-design/icons-vue'
import { PlusOutlined, SearchOutlined, UploadOutlined, PlayCircleOutlined } from '@ant-design/icons-vue'
import { VoiceService } from '@/api/voice'
import { MaterialService } from '@/api/material'
import dayjs from 'dayjs'
// ========== 常量定义 ==========
// ========== 常量 ==========
const POLLING_CONFIG = {
interval: 10000, // 轮询间隔：10秒
maxCount: 30, // 最大轮询次数：30次（5分钟）
transcriptionMaxLength: 50 // 识别内容最大显示长度
interval: 10000,
maxCount: 30,
transcriptionMaxLength: 50
}
const DEFAULT_FORM_DATA = {
@@ -254,18 +224,15 @@ const fillFormData = (data) => {
const loadVoiceList = async () => {
loading.value = true
try {
const params = {
const res = await VoiceService.getPage({
pageNo: pagination.current,
pageSize: pagination.pageSize,
name: searchParams.name || undefined
}
const res = await VoiceService.getPage(params)
if (res.code === 0) {
voiceList.value = res.data.list || []
pagination.total = res.data.total || 0
} else {
message.error(res.msg || '加载失败')
}
})
if (res.code !== 0) return message.error(res.msg || '加载失败')
voiceList.value = res.data.list || []
pagination.total = res.data.total || 0
} catch (error) {
console.error('加载配音列表失败:', error)
message.error('加载失败，请稍后重试')
@@ -303,14 +270,10 @@ const handleEdit = async (record) => {
formMode.value = 'edit'
try {
const res = await VoiceService.get(record.id)
if (res.code === 0 && res.data) {
fillFormData(res.data)
} else {
fillFormData(record) // 获取失败时使用列表数据
}
fillFormData(res.code === 0 && res.data ? res.data : record)
} catch (error) {
console.error('获取配音详情失败:', error)
fillFormData(record) // 异常时使用列表数据
fillFormData(record)
}
modalVisible.value = true
}
@@ -325,12 +288,10 @@ const handleDelete = (record) => {
onOk: async () => {
try {
const res = await VoiceService.delete(record.id)
if (res.code === 0) {
message.success('删除成功')
loadVoiceList()
} else {
message.error(res.msg || '删除失败')
}
if (res.code !== 0) return message.error(res.msg || '删除失败')
message.success('删除成功')
loadVoiceList()
} catch (error) {
console.error('删除失败:', error)
message.error('删除失败，请稍后重试')
@@ -344,13 +305,14 @@ const handleTranscribe = async (record) => {
transcribingId.value = record.id
try {
const res = await VoiceService.transcribe(record.id)
if (res.code === 0) {
message.success('识别任务已提交，正在识别中...')
startPollingTranscription(record.id)
} else {
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')
@@ -368,11 +330,11 @@ const stopPolling = () => {
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) {
@@ -381,7 +343,7 @@ const startPollingTranscription = (voiceId) => {
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')
@@ -389,9 +351,7 @@ const startPollingTranscription = (voiceId) => {
}
} catch (error) {
console.error('轮询识别结果失败:', error)
if (pollCount >= POLLING_CONFIG.maxCount) {
stopPolling()
}
if (pollCount >= POLLING_CONFIG.maxCount) stopPolling()
}
}, POLLING_CONFIG.interval)
}
@@ -408,79 +368,53 @@ const handlePlayAudio = (record) => {
// ========== 文件上传 ==========
const handleBeforeUpload = (file) => {
// 检查文件大小（100MB）
const MAX_FILE_SIZE = 100 * 1024 * 1024
const MAX_FILE_SIZE = 50 * 1024 * 1024
if (file.size > MAX_FILE_SIZE) {
message.error('文件大小不能超过 100MB')
message.error('文件大小不能超过 50MB')
return false
}
// 检查文件类型
const validTypes = ['audio/mpeg', 'audio/wav', 'audio/wave', 'audio/x-wav', 'audio/aac', 'audio/mp4', 'audio/flac', 'audio/ogg']
const validExtensions = ['.mp3', '.wav', '.aac', '.m4a', '.flac', '.ogg']
const fileName = file.name.toLowerCase()
const fileType = file.type.toLowerCase()
const isValidType = validTypes.some(type => fileType.includes(type)) ||
const isValidType = validTypes.some(type => fileType.includes(type)) ||
validExtensions.some(ext => fileName.endsWith(ext))
if (!isValidType) {
message.error('请上传音频文件（MP3、WAV、AAC、M4A、FLAC、OGG）')
return false
}
return true // 允许添加到文件列表
return true
}
const handleCustomUpload = async (options) => {
const { file, onSuccess, onError } = options
uploading.value = true
try {
const res = await MaterialService.uploadFile(file, 'voice', null)
if (res.code === 0) {
formData.fileId = res.data
message.success('文件上传成功')
// 使用 nextTick 确保 DOM 更新完成后再调用回调
await nextTick()
// 安全调用 onSuccess
if (onSuccess && typeof onSuccess === 'function') {
try {
onSuccess(res, file)
} catch (err) {
console.warn('onSuccess 回调执行失败:', err)
}
}
} else {
if (res.code !== 0) {
const errorMsg = res.msg || '上传失败'
message.error(errorMsg)
// 安全调用 onError
if (onError && typeof onError === 'function') {
try {
onError(new Error(errorMsg))
} catch (err) {
console.warn('onError 回调执行失败:', err)
}
}
onError?.(new Error(errorMsg))
return
}
formData.fileId = res.data
message.success('文件上传成功')
await nextTick()
onSuccess?.(res, file)
} catch (error) {
console.error('上传失败:', error)
const errorMsg = error?.message || '上传失败，请稍后重试'
message.error(errorMsg)
// 安全调用 onError
if (onError && typeof onError === 'function') {
try {
onError(error)
} catch (err) {
console.warn('onError 回调执行失败:', err)
}
}
onError?.(error)
} finally {
uploading.value = false
}
@@ -506,50 +440,50 @@ const handleRemoveFile = () => {
const handleSubmit = async () => {
try {
await formRef.value.validate()
submitting.value = true
} catch {
return
}
const params = isCreateMode.value
? {
name: formData.name,
fileId: formData.fileId,
autoTranscribe: formData.autoTranscribe,
language: formData.language,
gender: formData.gender,
note: formData.note
}
: {
id: formData.id,
name: formData.name,
language: formData.language,
gender: formData.gender,
note: formData.note,
transcription: formData.transcription
}
submitting.value = true
const params = isCreateMode.value
? {
name: formData.name,
fileId: formData.fileId,
autoTranscribe: formData.autoTranscribe,
language: formData.language,
gender: formData.gender,
note: formData.note
}
: {
id: formData.id,
name: formData.name,
language: formData.language,
gender: formData.gender,
note: formData.note,
transcription: formData.transcription
}
try {
const res = isCreateMode.value
? await VoiceService.create(params)
: await VoiceService.update(params)
if (res.code === 0) {
message.success(isCreateMode.value ? '创建成功' : '更新成功')
modalVisible.value = false
// 如果开启了自动识别，开始轮询识别结果
if (isCreateMode.value && formData.autoTranscribe && res.data) {
const voiceId = res.data
message.info('自动识别已启动，正在识别中...')
startPollingTranscription(voiceId)
}
loadVoiceList()
} else {
if (res.code !== 0) {
message.error(res.msg || '操作失败')
}
} catch (error) {
if (error?.errorFields) {
// 表单验证失败，不显示错误
return
}
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)
message.error('操作失败，请稍后重试')
} finally {
@@ -596,26 +530,18 @@ onUnmounted(() => {
align-items: center;
}
.page-title {
font-size: 20px;
font-weight: 600;
color: var(--color-text);
margin: 0;
line-height: 1.5;
display: flex;
align-items: center;
.search-bar,
.table-container {
background: var(--color-surface);
border-radius: var(--radius-card);
}
.search-bar {
margin-bottom: 16px;
padding: 16px;
background: var(--color-surface);
border-radius: var(--radius-card);
}
.table-container {
background: var(--color-surface);
border-radius: var(--radius-card);
padding: 16px;
}
@@ -630,20 +556,10 @@ onUnmounted(() => {
line-height: 1.5;
}
.uploaded-file-info {
margin-top: 8px;
}
.upload-hint {
font-size: 12px;
color: var(--color-text-secondary);
margin-top: 8px;
line-height: 1.5;
}
.form-hint {
font-size: 12px;
color: var(--color-text-secondary);
margin-top: 4px;
}
</style>

26
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/userprompt/controller/app/AppUserPromptController.java
View File

@@ -10,7 +10,6 @@ import cn.iocoder.yudao.module.tik.userprompt.vo.UserPromptRespVO;
import cn.iocoder.yudao.module.tik.userprompt.vo.UserPromptSaveReqVO;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.parameters.RequestBody;
import io.swagger.v3.oas.annotations.tags.Tag;
import jakarta.annotation.Resource;
import jakarta.validation.Valid;
@@ -33,34 +32,31 @@ public class AppUserPromptController {
@PostMapping("/create")
@Operation(summary = "创建用户提示词")
public CommonResult<Long> createUserPrompt(@RequestBody UserPromptSaveReqVO createReqVO) {
// 先设置当前登录用户ID（在验证之前设置，避免 @NotNull 验证失败）
public CommonResult<Long> createUserPrompt(@Valid @RequestBody UserPromptSaveReqVO createReqVO) {
// 设置当前登录用户ID
Long userId = getLoginUserId();
if (userId == null) {
return CommonResult.error(401, "用户未登录");
}
createReqVO.setUserId(userId);
// 手动验证必要字段
if (createReqVO.getName() == null || createReqVO.getName().trim().isEmpty()) {
return CommonResult.error(400, "提示词名称不能为空");
// 处理字符串字段的trim
if (createReqVO.getName() != null) {
createReqVO.setName(createReqVO.getName().trim());
}
if (createReqVO.getContent() == null || createReqVO.getContent().trim().isEmpty()) {
return CommonResult.error(400, "提示词内容不能为空");
}
if (createReqVO.getStatus() == null) {
return CommonResult.error(400, "状态不能为空");
if (createReqVO.getContent() != null) {
createReqVO.setContent(createReqVO.getContent().trim());
}
// 设置默认值（如果前端没有传递）
// 设置默认值
if (createReqVO.getIsPublic() == null) {
createReqVO.setIsPublic(false); // 默认私有
createReqVO.setIsPublic(false);
}
if (createReqVO.getSort() == null) {
createReqVO.setSort(0); // 默认排序为 0
createReqVO.setSort(0);
}
if (createReqVO.getUseCount() == null) {
createReqVO.setUseCount(0); // 默认使用次数为 0
createReqVO.setUseCount(0);
}
return success(userPromptService.createUserPrompt(createReqVO));

58
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/CosyVoiceClient.java
View File

@@ -86,27 +86,55 @@ public class CosyVoiceClient {
Map<String, Object> input = new HashMap<>();
input.put("text", request.getText());
String voiceId = StrUtil.blankToDefault(request.getVoiceId(), properties.getDefaultVoiceId());
if (StrUtil.isNotBlank(voiceId)) {
input.put("voice", voiceId);
// 优先使用fileUrl（语音克隆），否则使用voiceId（系统音色）
if (StrUtil.isNotBlank(request.getFileUrl())) {
// 直接使用预签名URL（带签名和时效），阿里云API需要这个签名URL
input.put("audio_url", request.getFileUrl());
log.info("[CosyVoice][使用语音克隆][audio_url={}]", request.getFileUrl());
// 如果提供了参考文本，也一并传递（用于提高语音克隆质量）
if (StrUtil.isNotBlank(request.getReferenceText())) {
input.put("reference_text", request.getReferenceText());
log.info("[CosyVoice][添加参考文本][length={}]", request.getReferenceText().length());
}
} else {
// 使用系统音色
String voiceId = StrUtil.blankToDefault(request.getVoiceId(), properties.getDefaultVoiceId());
if (StrUtil.isNotBlank(voiceId)) {
input.put("voice", voiceId);
log.info("[CosyVoice][使用系统音色][voice={}]", voiceId);
} else {
log.warn("[CosyVoice][未提供voiceId或fileUrl]");
}
}
payload.put("input", input);
Map<String, Object> parameters = new HashMap<>();
int sampleRate = request.getSampleRate() != null ? request.getSampleRate() : properties.getSampleRate();
parameters.put("sample_rate", sampleRate);
String format = StrUtil.blankToDefault(request.getAudioFormat(), properties.getAudioFormat());
// 根据官方文档，统一使用小写格式
String format = StrUtil.blankToDefault(request.getAudioFormat(), properties.getAudioFormat()).toLowerCase();
parameters.put("format", format);
if (request.getSpeechRate() != null) {
parameters.put("speech_rate", request.getSpeechRate());
}
if (request.getVolume() != null) {
parameters.put("volume", request.getVolume());
// 文档显示volume范围是0-100
parameters.put("volume", Math.round(request.getVolume()));
}
if (request.isPreview()) {
parameters.put("preview", true);
}
payload.put("parameters", parameters);
// 打印完整请求体（用于调试）
log.info("[CosyVoice][请求参数][model={}, sample_rate={}, format={}, text_length={}]",
model, sampleRate, format, request.getText().length());
return payload;
}
@@ -173,6 +201,26 @@ public class CosyVoiceClient {
return exception0(VOICE_TTS_FAILED.getCode(), body);
}
}
/**
* 从URL中提取原始URL（去除查询参数和锚点）
*
* @param url 可能包含查询参数的URL
* @return 原始URL（去除查询参数和锚点）
*/
private String extractRawUrl(String url) {
if (StrUtil.isBlank(url)) {
return url;
}
try {
java.net.URL urlObj = new java.net.URL(url);
// 只使用协议、主机、路径部分，忽略查询参数和锚点
return urlObj.getProtocol() + "://" + urlObj.getHost() + urlObj.getPath();
} catch (Exception e) {
// 如果URL解析失败，使用简单方式去除查询参数
return url.split("\\?")[0].split("#")[0];
}
}
}

10
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/client/dto/CosyVoiceTtsRequest.java
View File

@@ -20,6 +20,16 @@ public class CosyVoiceTtsRequest {
*/
private String voiceId;
/**
* 语音文件URL（当使用语音URL合成时使用，替代voiceId）
*/
private String fileUrl;
/**
* 参考音频文本（当使用fileUrl时，用于提高克隆质量）
*/
private String referenceText;
/**
* 模型（默认 cosyvoice-v2）
*/

394
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/service/TikUserVoiceServiceImpl.java
View File

@@ -91,8 +91,8 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
@Resource
private StringRedisTemplate stringRedisTemplate;
/** 预签名URL过期时间（1小时，单位：秒） */
private static final int PRESIGN_URL_EXPIRATION_SECONDS = 3600;
/** 预签名URL过期时间（24小时，单位：秒） */
private static final int PRESIGN_URL_EXPIRATION_SECONDS = 24 * 3600;
private static final String PREVIEW_CACHE_PREFIX = "tik:voice:preview:";
private static final String SYNTH_CACHE_PREFIX = "tik:voice:tts:";
private static final long PREVIEW_CACHE_TTL_SECONDS = 3600;
@@ -138,12 +138,18 @@ 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
// 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())) {
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);
// 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())) {
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());
}
}
log.info("[createVoice][用户({})创建配音成功，配音编号({})]", userId, voice.getId());
@@ -230,6 +236,10 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
// 查询配音列表
PageResult<TikUserVoiceDO> pageResult = voiceMapper.selectPage(pageReqVO);
// 增加日志：记录查询到的配音数量和用户ID
log.info("[getVoicePage][查询配音列表，用户ID={}, 总数={}]",
userId, pageResult.getTotal());
// 批量查询文件信息，避免 N+1 查询
Map<Long, FileDO> fileMap = new HashMap<>();
if (CollUtil.isNotEmpty(pageResult.getList())) {
@@ -237,7 +247,7 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
.map(TikUserVoiceDO::getFileId)
.distinct()
.collect(Collectors.toList());
if (CollUtil.isNotEmpty(fileIds)) {
List<FileDO> files = fileMapper.selectBatchIds(fileIds);
Map<Long, FileDO> tempFileMap = files.stream()
@@ -258,6 +268,12 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
vo.setFileUrl(presignedUrl);
}
// 增加日志：记录转换后的VO数据
if (log.isDebugEnabled()) {
log.debug("[getVoicePage][转换VO，配音ID={}, 名称={}]",
vo.getId(), vo.getName());
}
return vo;
});
}
@@ -297,28 +313,93 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
throw exception(VOICE_NOT_EXISTS);
}
// 2. 获取文件URL
// 2. 检查是否已经有识别结果
if (StrUtil.isNotBlank(voice.getTranscription())) {
log.info("[transcribeVoice][配音已经识别过，配音编号({})，跳过识别]", id);
return;
}
// 3. 获取文件URL
FileDO fileDO = fileMapper.selectById(voice.getFileId());
if (fileDO == null) {
throw exception(VOICE_FILE_NOT_EXISTS);
}
// 3. 异步执行识别
// 4. 异步执行识别
String fileAccessUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
asyncTranscribeVoice(id, fileAccessUrl);
}
@Override
public AppTikVoiceTtsRespVO synthesizeVoice(AppTikVoiceTtsReqVO reqVO) {
Long userId = SecurityFrameworkUtils.getLoginUserId();
Long voiceConfigId = reqVO.getVoiceConfigId();
// 增加请求参数日志
log.info("[synthesizeVoice][开始合成，请求参数：voiceConfigId={}, voiceId={}, fileUrl={}, userId={}]",
voiceConfigId, reqVO.getVoiceId(), reqVO.getFileUrl(), userId);
String voiceId = null;
String fileUrl = null;
String transcriptionText = null;
// 1. 如果有配置ID，根据配置ID查询配音信息（用户配音）
if (voiceConfigId != null) {
log.info("[synthesizeVoice][开始合成，配音编号({})，用户({})]", voiceConfigId, userId);
TikUserVoiceDO voice = voiceMapper.selectById(voiceConfigId);
log.info("[synthesizeVoice][查询配音结果：voice={},配音编号={},用户ID={}]",
voice != null ? "存在" : "不存在", voiceConfigId, userId);
if (voice == null) {
log.warn("[synthesizeVoice][配音不存在，配音编号({})，用户({})]", voiceConfigId, userId);
throw exception(VOICE_NOT_EXISTS, "配音不存在，编号：" + voiceConfigId);
}
if (!voice.getUserId().equals(userId)) {
log.warn("[synthesizeVoice][配音不属于当前用户，配音编号({})，配音用户({})，当前用户({})]",
voiceConfigId, voice.getUserId(), userId);
throw exception(VOICE_NOT_EXISTS, "配音不属于当前用户");
}
// 获取文件信息，用于获取文件URL
FileDO fileDO = fileMapper.selectById(voice.getFileId());
if (fileDO == null) {
throw exception(VOICE_FILE_NOT_EXISTS);
}
// 使用文件URL和识别文本进行合成
fileUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
transcriptionText = voice.getTranscription();
if (StrUtil.isBlank(transcriptionText)) {
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
if (StrUtil.isNotBlank(reqVO.getFileUrl()) && StrUtil.isBlank(reqVO.getTranscriptionText())) {
log.warn("[synthesizeVoice][使用fileUrl但未提供transcriptionText，可能影响克隆质量]");
}
// 参数验证：必须提供voiceId或fileUrl之一
if (StrUtil.isBlank(reqVO.getVoiceId()) && StrUtil.isBlank(reqVO.getFileUrl())) {
throw exception(VOICE_NOT_EXISTS, "请提供音色ID(voiceId)或语音文件URL(fileUrl)");
}
voiceId = reqVO.getVoiceId();
fileUrl = reqVO.getFileUrl();
transcriptionText = reqVO.getTranscriptionText();
}
String finalText = determineSynthesisText(
reqVO.getTranscriptionText(),
transcriptionText,
reqVO.getInputText(),
false);
finalText = appendEmotion(finalText, reqVO.getEmotion());
String cacheKey = buildCacheKey(SYNTH_CACHE_PREFIX,
reqVO.getVoiceId(),
reqVO.getFileUrl(),
voiceId,
fileUrl,
finalText,
reqVO.getSpeechRate(),
reqVO.getVolume(),
@@ -333,7 +414,9 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
CosyVoiceTtsResult ttsResult = cosyVoiceClient.synthesize(buildTtsRequest(
finalText,
reqVO.getVoiceId(),
voiceId,
fileUrl,
transcriptionText,
reqVO.getModel(),
reqVO.getSpeechRate(),
reqVO.getVolume(),
@@ -343,82 +426,186 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
));
String format = defaultFormat(ttsResult.getFormat(), reqVO.getAudioFormat());
String voiceId = StrUtil.blankToDefault(reqVO.getVoiceId(), cosyVoiceProperties.getDefaultVoiceId());
String finalVoiceId = StrUtil.blankToDefault(voiceId, cosyVoiceProperties.getDefaultVoiceId());
ByteArrayMultipartFile multipartFile = new ByteArrayMultipartFile(
"file",
buildFileName(voiceId, format),
buildFileName(finalVoiceId, format),
resolveContentType(format),
ttsResult.getAudio()
);
Long fileId = tikUserFileService.uploadFile(multipartFile, "audio", null);
Long infraFileId = tikUserFileService.uploadFile(multipartFile, "audio", null);
// 通过infraFileId查询TikUserFileDO，获取用户文件ID
TikUserFileDO userFile = userFileMapper.selectOne(
new LambdaQueryWrapperX<TikUserFileDO>()
.eq(TikUserFileDO::getFileId, infraFileId)
.eq(TikUserFileDO::getUserId, SecurityFrameworkUtils.getLoginUserId())
.orderByDesc(TikUserFileDO::getId)
.last("LIMIT 1"));
if (userFile == null) {
throw exception(VOICE_FILE_NOT_EXISTS, "文件上传成功但未找到用户文件记录");
}
AppTikVoiceTtsRespVO respVO = new AppTikVoiceTtsRespVO();
respVO.setFileId(fileId);
respVO.setAudioUrl(tikUserFileService.getAudioPlayUrl(fileId));
respVO.setFileId(infraFileId); // 返回infraFileId，保持与原有逻辑一致
respVO.setAudioUrl(tikUserFileService.getAudioPlayUrl(userFile.getId())); // 使用TikUserFileDO.id获取播放URL
respVO.setFormat(format);
respVO.setSampleRate(ttsResult.getSampleRate());
respVO.setRequestId(ttsResult.getRequestId());
respVO.setVoiceId(voiceId);
respVO.setVoiceId(finalVoiceId);
saveSynthCache(cacheKey, new SynthCacheEntry(
Base64.getEncoder().encodeToString(ttsResult.getAudio()),
format,
ttsResult.getSampleRate(),
ttsResult.getRequestId(),
voiceId
finalVoiceId
));
return respVO;
}
@Override
public AppTikVoicePreviewRespVO previewVoice(AppTikVoicePreviewReqVO reqVO) {
String finalText = determineSynthesisText(
reqVO.getTranscriptionText(),
reqVO.getInputText(),
true);
finalText = appendEmotion(finalText, reqVO.getEmotion());
Long userId = SecurityFrameworkUtils.getLoginUserId();
Long voiceConfigId = reqVO.getVoiceConfigId();
// 增加请求参数日志
log.info("[previewVoice][开始试听，请求参数：voiceConfigId={}, voiceId={}, fileUrl={}, userId={}]",
voiceConfigId, reqVO.getVoiceId(), reqVO.getFileUrl(), userId);
String voiceId = null;
String fileUrl = null;
String transcriptionText = null;
String inputText;
// 1. 如果传入了fileUrl和transcriptionText，直接使用（通过语音URL合成）
if (StrUtil.isNotBlank(reqVO.getFileUrl()) && StrUtil.isNotBlank(reqVO.getTranscriptionText())) {
log.info("[previewVoice][使用语音URL合成，用户({})]", userId);
// 如果传入的是预签名URL，提取原始URL（去除查询参数），避免二次签名
String rawFileUrl = extractRawUrl(reqVO.getFileUrl());
// 如果提取后的URL与原始URL不同，说明是预签名URL，需要重新生成预签名URL
// 否则直接使用（可能是原始URL或公开URL）
if (!rawFileUrl.equals(reqVO.getFileUrl())) {
// 重新生成预签名URL，确保有效期足够长
fileUrl = fileApi.presignGetUrl(rawFileUrl, PRESIGN_URL_EXPIRATION_SECONDS);
log.info("[previewVoice][检测到预签名URL，已提取原始URL并重新生成预签名URL]");
} else {
fileUrl = reqVO.getFileUrl();
}
transcriptionText = reqVO.getTranscriptionText();
inputText = StrUtil.blankToDefault(reqVO.getInputText(), transcriptionText);
}
// 2. 如果有配置ID，根据配置ID查询配音信息（用户配音）
else if (voiceConfigId != null) {
log.info("[previewVoice][开始试听，配音编号({})，用户({})]", voiceConfigId, userId);
TikUserVoiceDO voice = voiceMapper.selectById(voiceConfigId);
log.info("[previewVoice][查询配音结果：voice={},配音编号={},用户ID={}]",
voice != null ? "存在" : "不存在", voiceConfigId, userId);
if (voice == null) {
log.warn("[previewVoice][配音不存在，配音编号({})，用户({})]", voiceConfigId, userId);
throw exception(VOICE_NOT_EXISTS, "配音不存在，编号：" + voiceConfigId);
}
if (!voice.getUserId().equals(userId)) {
log.warn("[previewVoice][配音不属于当前用户，配音编号({})，配音用户({})，当前用户({})]",
voiceConfigId, voice.getUserId(), userId);
throw exception(VOICE_NOT_EXISTS, "配音不属于当前用户");
}
// 获取文件信息，用于获取文件URL
FileDO fileDO = fileMapper.selectById(voice.getFileId());
if (fileDO == null) {
throw exception(VOICE_FILE_NOT_EXISTS);
}
// 使用文件URL和识别文本进行合成
fileUrl = fileApi.presignGetUrl(fileDO.getUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
transcriptionText = voice.getTranscription();
if (StrUtil.isBlank(transcriptionText)) {
throw exception(VOICE_NOT_EXISTS, "配音识别文本为空，请先进行语音识别");
}
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);
voiceId = StrUtil.blankToDefault(reqVO.getVoiceId(), cosyVoiceProperties.getDefaultVoiceId());
if (StrUtil.isBlank(voiceId)) {
throw exception(VOICE_NOT_EXISTS, "系统配音音色ID不能为空");
}
inputText = StrUtil.blankToDefault(reqVO.getInputText(), cosyVoiceProperties.getPreviewText());
}
String finalText = determineSynthesisText(
transcriptionText,
inputText,
true);
// 使用请求参数或默认值
String emotion = StrUtil.blankToDefault(reqVO.getEmotion(), "neutral");
finalText = appendEmotion(finalText, emotion);
Float speechRate = reqVO.getSpeechRate() != null ? reqVO.getSpeechRate() : 1.0f;
Float volume = reqVO.getVolume() != null ? reqVO.getVolume() : 0f;
String audioFormat = StrUtil.blankToDefault(reqVO.getAudioFormat(), "mp3");
// 构建缓存key（使用fileUrl或voiceId）
String cacheKey = buildCacheKey(PREVIEW_CACHE_PREFIX,
reqVO.getVoiceId(),
reqVO.getFileUrl(),
voiceId,
fileUrl,
finalText,
reqVO.getSpeechRate(),
reqVO.getVolume(),
reqVO.getEmotion(),
reqVO.getAudioFormat(),
speechRate,
volume,
emotion,
audioFormat,
null);
PreviewCacheEntry previewCache = getPreviewCache(cacheKey);
String voiceId = StrUtil.blankToDefault(reqVO.getVoiceId(), cosyVoiceProperties.getDefaultVoiceId());
if (previewCache != null) {
log.info("[previewVoice][使用缓存，配音编号({})，voiceId({})，fileUrl({})，cacheKey({})]",
voiceConfigId, voiceId, fileUrl, cacheKey);
// 缓存中存储的是原始URL，需要生成预签名URL
String cachedUrl = fileApi.presignGetUrl(previewCache.getFileUrl(), PRESIGN_URL_EXPIRATION_SECONDS);
return buildPreviewResp(previewCache, cachedUrl, voiceId);
}
log.info("[previewVoice][调用CosyVoice合成，配音编号({})，voiceId({})，fileUrl({})，文本长度({})]",
voiceConfigId, voiceId, fileUrl, finalText.length());
CosyVoiceTtsResult ttsResult = cosyVoiceClient.synthesize(buildTtsRequest(
finalText,
reqVO.getVoiceId(),
reqVO.getModel(),
reqVO.getSpeechRate(),
reqVO.getVolume(),
voiceId,
fileUrl,
transcriptionText, // 参考音频文本，用于提高克隆质量
null, // 使用默认模型
speechRate,
volume,
null,
reqVO.getAudioFormat(),
audioFormat,
true
));
String format = defaultFormat(ttsResult.getFormat(), reqVO.getAudioFormat());
voiceId = StrUtil.blankToDefault(reqVO.getVoiceId(), cosyVoiceProperties.getDefaultVoiceId());
String objectName = buildFileName(voiceId, format);
String fileUrl = fileApi.createFile(ttsResult.getAudio(), objectName, "voice/preview", resolveContentType(format));
String presignUrl = fileApi.presignGetUrl(fileUrl, PRESIGN_URL_EXPIRATION_SECONDS);
PreviewCacheEntry entry = new PreviewCacheEntry(fileUrl, format, ttsResult.getSampleRate(), ttsResult.getRequestId());
String format = defaultFormat(ttsResult.getFormat(), audioFormat);
String identifier = StrUtil.isNotBlank(fileUrl) ? "fileUrl" : (StrUtil.isNotBlank(voiceId) ? voiceId : "voice");
String objectName = buildFileName(identifier, format);
// 上传到OSS，返回原始URL（不是预签名URL）
String resultFileUrl = fileApi.createFile(ttsResult.getAudio(), objectName, "voice/preview", resolveContentType(format));
log.info("[previewVoice][合成成功，配音编号({})，voiceId({})，fileUrl({})，resultFileUrl({})，format({})]",
voiceConfigId, voiceId, fileUrl, resultFileUrl, format);
// 生成预签名URL用于返回给前端
String presignUrl = fileApi.presignGetUrl(resultFileUrl, PRESIGN_URL_EXPIRATION_SECONDS);
// 缓存中存储原始URL（不是预签名URL），下次使用时再生成预签名URL
PreviewCacheEntry entry = new PreviewCacheEntry(resultFileUrl, format, ttsResult.getSampleRate(), ttsResult.getRequestId());
savePreviewCache(cacheKey, entry);
return buildPreviewResp(entry, presignUrl, voiceId);
}
private CosyVoiceTtsRequest buildTtsRequest(String text,
String voiceId,
String fileUrl,
String referenceText,
String model,
Float speechRate,
Float volume,
@@ -428,6 +615,8 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
return CosyVoiceTtsRequest.builder()
.text(text)
.voiceId(voiceId)
.fileUrl(fileUrl)
.referenceText(referenceText)
.model(model)
.speechRate(speechRate)
.volume(volume)
@@ -500,6 +689,26 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
return "【情感：" + emotionLabel + "】" + text;
}
/**
* 从URL中提取原始URL（去除查询参数和锚点）
*
* @param url 可能包含查询参数的URL
* @return 原始URL（去除查询参数和锚点）
*/
private String extractRawUrl(String url) {
if (StrUtil.isBlank(url)) {
return url;
}
try {
java.net.URL urlObj = new java.net.URL(url);
// 只使用协议、主机、路径部分，忽略查询参数和锚点
return urlObj.getProtocol() + "://" + urlObj.getHost() + urlObj.getPath();
} catch (Exception e) {
// 如果URL解析失败，使用简单方式去除查询参数
return url.split("\\?")[0].split("#")[0];
}
}
private String buildCacheKey(String prefix,
String voiceId,
String fileUrl,
@@ -509,9 +718,17 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
String emotion,
String audioFormat,
Integer sampleRate) {
String identifier = StrUtil.isNotBlank(voiceId)
? voiceId
: StrUtil.blankToDefault(fileUrl, "no-voice");
// 构建标识符：优先使用voiceId，如果没有则使用fileUrl的稳定部分（去除查询参数）
String identifier;
if (StrUtil.isNotBlank(voiceId)) {
identifier = voiceId;
} else if (StrUtil.isNotBlank(fileUrl)) {
// 对于fileUrl，提取稳定部分（去除预签名URL的查询参数，避免缓存key不稳定）
identifier = extractRawUrl(fileUrl);
} else {
identifier = "no-voice";
}
String payload = StrUtil.join("|",
identifier,
text,
@@ -584,11 +801,22 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
resolveContentType(format),
audioBytes
);
Long fileId = tikUserFileService.uploadFile(multipartFile, "audio", null);
Long infraFileId = tikUserFileService.uploadFile(multipartFile, "audio", null);
// 通过infraFileId查询TikUserFileDO，获取用户文件ID
TikUserFileDO userFile = userFileMapper.selectOne(
new LambdaQueryWrapperX<TikUserFileDO>()
.eq(TikUserFileDO::getFileId, infraFileId)
.eq(TikUserFileDO::getUserId, SecurityFrameworkUtils.getLoginUserId())
.orderByDesc(TikUserFileDO::getId)
.last("LIMIT 1"));
if (userFile == null) {
throw exception(VOICE_FILE_NOT_EXISTS, "文件上传成功但未找到用户文件记录");
}
AppTikVoiceTtsRespVO respVO = new AppTikVoiceTtsRespVO();
respVO.setFileId(fileId);
respVO.setAudioUrl(tikUserFileService.getAudioPlayUrl(fileId));
respVO.setFileId(infraFileId); // 返回infraFileId，保持与原有逻辑一致
respVO.setAudioUrl(tikUserFileService.getAudioPlayUrl(userFile.getId())); // 使用TikUserFileDO.id获取播放URL
respVO.setFormat(format);
respVO.setSampleRate(cache.getSampleRate());
respVO.setRequestId(cache.getRequestId());
@@ -685,21 +913,40 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
@Async
public void asyncTranscribeVoice(Long voiceId, String fileUrl) {
try {
// 1. 检查是否已经识别过（防重复）
TikUserVoiceDO existingVoice = voiceMapper.selectById(voiceId);
if (existingVoice == null) {
log.warn("[asyncTranscribeVoice][配音记录不存在，配音编号({})]", voiceId);
return;
}
// 如果已经有识别结果，不再重复识别
if (StrUtil.isNotBlank(existingVoice.getTranscription())) {
log.info("[asyncTranscribeVoice][配音已经识别过，配音编号({})，跳过识别]", voiceId);
return;
}
log.info("[asyncTranscribeVoice][开始识别，配音编号({})，文件URL({})]", voiceId, fileUrl);
Object result = tikHupService.videoToCharacters2(Collections.singletonList(fileUrl));
// 解析识别结果
String transcription = extractTranscription(result);
if (StrUtil.isNotBlank(transcription)) {
// 更新识别结果
TikUserVoiceDO updateObj = new TikUserVoiceDO()
.setId(voiceId)
.setTranscription(transcription);
voiceMapper.updateById(updateObj);
log.info("[asyncTranscribeVoice][识别成功，配音编号({})，文本长度({})]", voiceId, transcription.length());
// 二次检查：解析后再次检查是否已经有识别结果（避免并发重复）
TikUserVoiceDO currentVoice = voiceMapper.selectById(voiceId);
if (currentVoice != null && StrUtil.isBlank(currentVoice.getTranscription())) {
// 更新识别结果
TikUserVoiceDO updateObj = new TikUserVoiceDO()
.setId(voiceId)
.setTranscription(transcription);
voiceMapper.updateById(updateObj);
log.info("[asyncTranscribeVoice][识别成功，配音编号({})，文本长度({})]", voiceId, transcription.length());
} else {
log.info("[asyncTranscribeVoice][并发跳过更新，配音编号({})已经有识别结果]", voiceId);
}
} else {
log.warn("[asyncTranscribeVoice][识别结果为空，配音编号({})，返回码({})]",
log.warn("[asyncTranscribeVoice][识别结果为空，配音编号({})，返回码({})]",
voiceId, result instanceof CommonResult ? ((CommonResult<?>) result).getCode() : "未知");
}
} catch (Exception e) {
@@ -773,17 +1020,28 @@ public class TikUserVoiceServiceImpl implements TikUserVoiceService {
if (CollUtil.isEmpty(results)) {
return null;
}
Object lastObj = results.get(results.size() - 1);
if (!(lastObj instanceof JSONObject lastResult)) {
// 阿里云语音识别：取第一个结果即可
Object firstObj = results.get(0);
if (!(firstObj instanceof JSONObject firstResult)) {
return null;
}
String transcriptionUrl = lastResult.getStr("transcription_url");
if (StrUtil.isBlank(transcriptionUrl)) {
return null;
// 先从第一个结果中直接提取文本
String directText = extractTextFromJson(firstResult);
if (StrUtil.isNotBlank(directText)) {
return directText;
}
StringBuilder builder = new StringBuilder();
appendRemoteTranscription(builder, transcriptionUrl);
return builder.length() > 0 ? builder.toString().trim() : null;
// 如果没有直接文本，尝试获取 transcription_url
String transcriptionUrl = firstResult.getStr("transcription_url");
if (StrUtil.isNotBlank(transcriptionUrl)) {
StringBuilder builder = new StringBuilder();
appendRemoteTranscription(builder, transcriptionUrl);
return builder.length() > 0 ? builder.toString().trim() : null;
}
return null;
}
} catch (Exception e) {
log.warn("[parseTranscriptionText][解析Paraformer结果失败]", e);

37
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/vo/AppTikVoicePreviewReqVO.java
View File

@@ -1,6 +1,7 @@
package cn.iocoder.yudao.module.tik.voice.vo;
import io.swagger.v3.oas.annotations.media.Schema;
import jakarta.validation.constraints.NotNull;
import jakarta.validation.constraints.Size;
import lombok.Data;
@@ -10,33 +11,33 @@ import lombok.Data;
@Data
public class AppTikVoicePreviewReqVO {
@Schema(description = "输入文本")
@Schema(description = "配音编号（tik_user_voice.id），用户配音必传，系统配音可不传")
private Long voiceConfigId;
@Schema(description = "CosyVoice音色ID（系统配音必传，用户配音可不传）")
private String voiceId;
@Schema(description = "语音文件URL（当使用语音URL合成时必传，替代voiceId）")
private String fileUrl;
@Schema(description = "语音文本/识别文本（当使用fileUrl时必传）")
@Size(max = 4000, message = "语音文本不能超过 4000 个字符")
private String transcriptionText;
@Schema(description = "输入文本（可选，如果不传则使用配音的识别文本或默认文本）")
@Size(max = 4000, message = "输入文本不能超过 4000 个字符")
private String inputText;
@Schema(description = "识别文本，用于拼接")
@Size(max = 4000, message = "识别文本不能超过 4000 个字符")
private String transcriptionText;
@Schema(description = "音色 ID（CosyVoice voiceId）")
private String voiceId;
@Schema(description = "音色源音频 OSS 地址（当没有 voiceId 时必传）")
private String fileUrl;
@Schema(description = "模型名称，默认 cosyvoice-v2")
private String model;
@Schema(description = "语速", example = "1.0")
@Schema(description = "语速（可选，默认1.0）", example = "1.0")
private Float speechRate;
@Schema(description = "音量", example = "0")
@Schema(description = "音量（可选，默认0）", example = "0")
private Float volume;
@Schema(description = "情感", example = "neutral")
@Schema(description = "情感（可选，默认neutral）", example = "neutral")
private String emotion;
@Schema(description = "音频格式，默认 wav")
@Schema(description = "音频格式（可选，默认mp3）", example = "mp3")
private String audioFormat;
}

3
yudao-module-tik/src/main/java/cn/iocoder/yudao/module/tik/voice/vo/AppTikVoiceTtsReqVO.java
View File

@@ -14,6 +14,9 @@ public class AppTikVoiceTtsReqVO {
@Size(max = 4000, message = "输入文本不能超过 4000 个字符")
private String inputText;
@Schema(description = "配音编号（tik_user_voice.id），用户配音必传，系统配音可不传")
private Long voiceConfigId;
@Schema(description = "识别文本，用于拼接")
@Size(max = 4000, message = "识别文本不能超过 4000 个字符")
private String transcriptionText;

2
yudao-server/src/main/resources/application.yaml
View File

@@ -12,7 +12,7 @@ spring:
servlet:
# 文件上传相关配置项
multipart:
max-file-size: 100MB # 单个文件大小
max-file-size: 100MB # 单个文件大小（配音文件建议50MB以内）
max-request-size: 200MB # 设置总上传的文件大小（支持多文件上传）
# Jackson 配置项