官方文档:https://platform.vidu.cn/docs/text-to-speech
POST
/ent/v2/audio-tts语音合成
API Key application/json
请求示例
curl -X POST https://top.qingyuntop.ai/ent/v2/audio-tts \
-H "Authorization: Bearer ${QINGYUN_TOP_API_KEY}" \
-H "Content-Type: application/json" \
-d '{
"text": "人工智能正在改变我们的生活方式,从智能家居到自动驾驶,技术的进步让世界变得更加便利。",
"voice_setting_voice_id": "male-qn-daxuesheng"
}'请求参数
| 参数 | 位置 | 类型 | 必填 | 说明 | 示例 |
|---|---|---|---|---|---|
Authorization | Header | string | 否 | - | Bearer {{YOUR_API_KEY}} |
Content-Type | Header | string | 否 | - | application/json |
text | JSON body | string | 是 | 需要合成语音的文本 1. 长度限制小于 10000 字符 2. 段落切换用换行符标记 3. 停顿控制:支持自定义文本之间的语音时间间隔,以实现自定义文本语音停顿时间的效果。 - 使用方式:在文本中增加<#x#>标记,x 为停顿时长(单位:秒),范围 [0.01, 99.99],最多保留两位小数。文本间隔时间需设置在两个可以语音发音的文本之间,不可连续使用多个停顿标记 - 示例:你好<#2#>我是vidu<#2#>很高兴见到你 | - |
voice_setting_voice_id | JSON body | string | 是 | 合成音频的音色id 可查看音色列表查询全部可用音色:https://shengshu.feishu.cn/sheets/EgFvs6DShhiEBStmjzccr5gonOg | - |
voice_setting_speed | JSON body | string | 否 | 语速,默认为1.0 1.0为正常语速,范围 [0.5,2],值为0.5时播报语速最慢,值为2时播报语速最快 | - |
voice_setting_volume | JSON body | string | 否 | 音量大小 范围 0 - 10,默认为0,代表正常音量,值越大音量越高 | - |
voice_setting_pitch | JSON body | string | 否 | 合成音频的语调 范围 [-12,12],默认 0,其中 0 为原音色输出 | - |
voice_setting_emotion | JSON body | string | 否 | 控制合成语音的情绪 1. 参数范围 ["happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm"],分别对应 7 种情绪:高兴,悲伤,愤怒,害怕,厌恶,惊讶,中性 2. 模型会根据输入文本自动匹配合适的情绪,一般无需手动指定 | - |
pronunciation_dict_tone | JSON body | string | 否 | 定义多音字发音 - 定义需要特殊标注的文字或符号对应的注音或发音替换规则,针对多音字场景,在中文文本中,声调用数字表示:一声为 1;二声为 2;三声为 3;四声为 4;轻声为 5。 - 示例如下: ["燕少飞/(yan4)(shao3)(fei1)", "达菲/(da2)(fei1)", "omg/oh my god"] | - |
payload | JSON body | string | 否 | 透传参数 不做任何处理,仅数据传输 注:最多 1048576个字符 | - |
返回响应 (200)
| 参数 | 位置 | 类型 | 必填 | 说明 | 示例 |
|---|---|---|---|---|---|
task_id | 响应 JSON | string | 是 | - | - |
state | 响应 JSON | string | 是 | - | - |
model | 响应 JSON | string | 是 | - | - |
prompt | 响应 JSON | string | 是 | - | - |
duration | 响应 JSON | integer | 是 | - | - |
seed | 响应 JSON | integer | 是 | - | - |
created_at | 响应 JSON | string | 是 | - | - |
credits | 响应 JSON | integer | 是 | - | - |
响应示例
{
"task_id": "911094612548939776",
"state": "created",
"model": "audio1.0",
"prompt": "雨滴落在窗户上的声音,伴随着轻柔的雷声",
"duration": 5,
"seed": 0,
"created_at": "2026-01-20T07:16:38.094635957Z",
"credits": 10
}来源原始接口定义(用于追溯)
以下内容来自 Apifox 快照,可能包含兼容层字段或旧示例;公开调用请以本页的协议说明和当前模型列表为准。
{
"id": 495899880,
"name": "语音合成",
"type": "http",
"serverId": "",
"preProcessors": [],
"postProcessors": [],
"inheritPreProcessors": {},
"inheritPostProcessors": {},
"description": "官方文档:https://platform.vidu.cn/docs/text-to-speech",
"operationId": "",
"sourceUrl": "",
"method": "post",
"path": "/ent/v2/audio-tts",
"tags": [],
"status": 1,
"requestBody": {
"type": "application/json",
"parameters": [],
"jsonSchema": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "需要合成语音的文本\n1. 长度限制小于 10000 字符\n2. 段落切换用换行符标记\n3. 停顿控制:支持自定义文本之间的语音时间间隔,以实现自定义文本语音停顿时间的效果。\n- 使用方式:在文本中增加<#x#>标记,x 为停顿时长(单位:秒),范围 [0.01, 99.99],最多保留两位小数。文本间隔时间需设置在两个可以语音发音的文本之间,不可连续使用多个停顿标记\n- 示例:你好<#2#>我是vidu<#2#>很高兴见到你"
},
"voice_setting_voice_id": {
"type": "string",
"description": "合成音频的音色id\n可查看音色列表查询全部可用音色:https://shengshu.feishu.cn/sheets/EgFvs6DShhiEBStmjzccr5gonOg"
},
"voice_setting_speed": {
"type": "string",
"description": "语速,默认为1.0\n1.0为正常语速,范围 [0.5,2],值为0.5时播报语速最慢,值为2时播报语速最快"
},
"voice_setting_volume": {
"type": "string",
"description": "音量大小\n范围 0 - 10,默认为0,代表正常音量,值越大音量越高"
},
"voice_setting_pitch": {
"type": "string",
"description": "合成音频的语调\n范围 [-12,12],默认 0,其中 0 为原音色输出"
},
"voice_setting_emotion": {
"type": "string",
"description": "控制合成语音的情绪\n1. 参数范围 [\"happy\", \"sad\", \"angry\", \"fearful\", \"disgusted\", \"surprised\", \"calm\"],分别对应 7 种情绪:高兴,悲伤,愤怒,害怕,厌恶,惊讶,中性\n2. 模型会根据输入文本自动匹配合适的情绪,一般无需手动指定"
},
"pronunciation_dict_tone": {
"type": "string",
"description": "定义多音字发音\n- 定义需要特殊标注的文字或符号对应的注音或发音替换规则,针对多音字场景,在中文文本中,声调用数字表示:一声为 1;二声为 2;三声为 3;四声为 4;轻声为 5。\n- 示例如下:\n[\"燕少飞/(yan4)(shao3)(fei1)\", \"达菲/(da2)(fei1)\", \"omg/oh my god\"]"
},
"payload": {
"type": "string",
"description": "透传参数\n不做任何处理,仅数据传输\n注:最多 1048576个字符"
}
},
"required": [
"text",
"voice_setting_voice_id"
],
"x-apifox-orders": [
"text",
"voice_setting_voice_id",
"voice_setting_speed",
"voice_setting_volume",
"voice_setting_pitch",
"voice_setting_emotion",
"pronunciation_dict_tone",
"payload"
]
},
"examples": [
{
"mediaType": "application/json",
"value": "{\r\n \"text\": \"人工智能正在改变我们的生活方式,从智能家居到自动驾驶,技术的进步让世界变得更加便利。\",\r\n \"voice_setting_voice_id\": \"male-qn-daxuesheng\"\r\n}"
}
],
"mediaType": "",
"oasExtensions": "",
"required": false,
"additionalContentTypes": []
},
"parameters": {
"path": [],
"query": [],
"cookie": [],
"header": [
{
"id": "Jsj23RwEo1",
"name": "Authorization",
"required": false,
"enable": true,
"description": "",
"type": "string",
"sampleValue": "Bearer {{YOUR_API_KEY}}"
},
{
"id": "jjYSOg2NrR",
"name": "Content-Type",
"required": false,
"enable": true,
"description": "",
"type": "string",
"sampleValue": "application/json"
}
]
},
"commonParameters": {
"query": [],
"body": [],
"cookie": [],
"header": []
},
"auth": {
"type": "inherit",
"inherit": {}
},
"responses": [
{
"id": 199428446,
"name": "成功",
"code": 200,
"contentType": "json",
"jsonSchema": {
"type": "object",
"properties": {
"task_id": {
"type": "string"
},
"state": {
"type": "string"
},
"model": {
"type": "string"
},
"prompt": {
"type": "string"
},
"duration": {
"type": "integer"
},
"seed": {
"type": "integer"
},
"created_at": {
"type": "string"
},
"credits": {
"type": "integer"
}
},
"required": [
"task_id",
"state",
"model",
"prompt",
"duration",
"seed",
"created_at",
"credits"
],
"x-apifox-orders": [
"task_id",
"state",
"model",
"prompt",
"duration",
"seed",
"created_at",
"credits"
]
},
"itemSchema": {},
"description": "",
"mediaType": "",
"headers": [],
"oasExtensions": ""
}
],
"responseExamples": [
{
"name": "成功示例",
"responseId": 199428446,
"data": "{\r\n \"task_id\": \"911094612548939776\",\r\n \"state\": \"created\",\r\n \"model\": \"audio1.0\",\r\n \"prompt\": \"雨滴落在窗户上的声音,伴随着轻柔的雷声\",\r\n \"duration\": 5,\r\n \"seed\": 0,\r\n \"created_at\": \"2026-01-20T07:16:38.094635957Z\",\r\n \"credits\": 10\r\n}",
"description": "",
"oasKey": "",
"oasExtensions": "",
"id": "019fc09b-0b31-75fd-9d7e-1a1e7ceb137d"
}
],
"codeSamples": [],
"projectId": 8662722,
"moduleId": 8310462,
"folderId": 92436088,
"ordering": 24,
"responsibleId": 0,
"commonResponseStatus": {},
"advancedSettings": {
"disabledSystemHeaders": {}
},
"customApiFields": {},
"oasExtensions": "",
"mockScript": {},
"createdAt": "2026-08-02T03:53:34.000Z",
"updatedAt": "2026-08-06T12:15:55.000Z",
"creatorId": 2863449,
"editorId": 2863449,
"creatorUserId": 2863449,
"editorUserId": 2863449,
"responseChildren": [],
"visibility": "INHERITED",
"securityScheme": {},
"callbacks": ""
}