TTS Asynchronous Generation Documentation

Request URL and Headers

https://tts-api.dubbingx.com/

Note: All requests in this document use the POST method.

Common Request Headers

Parameter	Value
Authorization	Bearer apiKey
Content-Type	application/json

apiKey is the user's API key. which can be generated in the client

1-1. Retrieve Voice List

/v1/getTTSTimbreList

Request Parameters

{"pageIndex":1,"pageSize":100}

Response

Field	Description
id	Voice ID
grade	premium for multilingual; ordinary for monolingual
gender	0 for female; 1 for male；
voiceUrl	URL for voice sample

{
    "code": 200,
    "success": true,
    "msg": "操作成功",
    "data": {
        "total": 1,
        "list": [
            {
                "id": "30002",
                "grade": "premium",
                "isOfficial": true,
                "name": "智吾褚",
                "description": "中青年  稳重   温暖",//Middle-aged, calm, warm
                "gender": 1,
                "avatar": "https://public.dubbingx.com/avatar/10092/20240329-143217.png",
                "voiceUrl": "https://public.dubbingx.com/audition/10092/mujin.wav",
                "status": true,
                "createTime": "2023-11-03 18:24:12"
            }
        ]
    },
    "time": "2024-04-10 16:24:55",
    "traceId": "1777976038257512450"
}

1-2. Analyze Emotion from Text (Optional)

/v2/analyzeEmotion

Field	Description
text	Text content to be analyzed

Example Request:

{
	"text": "The weather is great today!!"
}

Response

Field	Description
data	Returned emotion and level

{
  "code": 200,
  "success": true,
  "msg": "操作成功",
  "data": "开心-正常-3",//meanings Happy-Normal-3
  "time": "2024-09-02 11:23:05",
  "traceId": "1830446316581281793"
}

2.Send TTS Synthesis Command (Asynchronous Result)

/v2/addTtsTask

V2 version uses SSML format

Field	Description
text	SSML formatted string

SSML Filed	Description
voiceId	Voice ID obtained from getTTSTimbreList
emotion	Emotion from emotion data url, each emotion has 5 levels. Do not pass for monolingual; leave empty for multilingual to support automatic emotion detection. Users need to concatenate and pass the emotion. First, take the outermost type, such as "常规"（Displayed in English as General）; then take the second-level aura, such as "日常说话"(Displayed in English as Daily Talk); and finally, append the intensity, ranging from 1 to 5. The concatenated result will be similar to: 常规-日常说话-3
language	zh for Chinese, jp for Japanese, en for English, yue for Cantonese
audioPitch	Pitch, 1.0 is the original pitch, range from 0.7 to 1.3
audioSpeed	Speed, 1.0 is the original speed, range from 0.7 to 1.3
phoneme	Phoneme annotation, only supports Chinese, wrap a single character per annotation, multiple characters require multiple annotations. Format: <phoneme ph="duan2">段</phoneme>

Example Request:

{
    "text": "<speak voiceId=\"30065\" language=\"zh\" emotion=\"常规-日常说话-3\" audioPitch=\"1.1\" audioSpeed=\"1.1\">这是一<phoneme ph=\"duan2\">段</phoneme>测试音频！</speak>"
}

Response

Field	Description
taskId	Task ID returned after successfully adding the task

{
    "code": 200,
    "success": true,
    "msg": "操作成功",//Operation successful
    "data": {
        "taskId": "1778319033905385473"
    },
    "time": "2024-04-11 15:07:52",
    "traceId": "1778319033238491137"
}

3.Retrieve Synthesis Status

v1/getTtsTaskInfo/${taskId}

Request Parameters Append taskId to the URL.

MeThod:POST

Response

Field	Description
status	Ready for synthesis, Transitioning, Completed ,Failed. When status is Completed, the fileUrl will return the synthesized audio download link.

{
    "code": 200,
    "success": true,
    "msg": "操作成功",
    "data": {
        "id": "1778319033905385473",
        "status": "Completed",
        "language": "zh",
        "fileName": "dce642383ca447b3ac4ed57cd3e5b2b4.wav",
        "fileUrl": "https://tts-bucket.dubbingx.com/10092/30002/dce642383ca447b3ac4ed57cd3e5b2b4.wav?Expires=1712849799&OSSAccessKeyId=LTAI5t8FMBqtNy467wQoCC3t&Signature=x7wCkhlQlCI8DPNdP8kLoPkvk0w%3D",
        "updateTime": "2024-04-11 15:07:59",
        "createTime": "2024-04-11 15:07:52"
    },
    "time": "2024-04-11 15:36:39",
    "traceId": "1778326277661331458"
}

3-1.Retrieve Synthesis Status in Batch

v1/getTtsTaskListInfo Request Body Raw: Json

["1778328789218971650","1778328790586314754","1778328790703755265","1778328790888304642"]

Example Response:

{
    "code": 200,
    "success": true,
    "msg": "操作成功",
    "data": [
        {
            "id": "1778328789218971650",
            "status": "Completed",
            "language": "zh",
            "fileName": "61a74e1801ef4984ac0c911e815efaa1.wav",
            "fileUrl": "",
            "updateTime": "2024-04-11 15:46:43",
            "createTime": "2024-04-11 15:46:38"
        },
        {
            "id": "1778328790586314754",
            "status": "Completed",
            "language": "zh",
            "fileName": "eb80e60b17bc457db8e37fe0051fd020.wav",
            "fileUrl": "",
            "updateTime": "2024-04-11 15:46:46",
            "createTime": "2024-04-11 15:46:38"
        },
        {
            "id": "1778328790703755265",
            "status": "Completed",
            "language": "zh",
            "fileName": "e74b9d83d1134aafb1b82a9626166756.wav",
            "fileUrl": "",
            "updateTime": "2024-04-11 15:46:48",
            "createTime": "2024-04-11 15:46:38"
        },
        {
            "id": "1778328790888304642",
            "status": "Completed",
            "language": "zh",
            "fileName": "52ec6be56d2346a6a9847553d51c5094.wav",
            "fileUrl": "",
            "updateTime": "2024-04-11 15:46:51",
            "createTime": "2024-04-11 15:46:38"
        }
    ],
    "time": "2024-04-11 15:47:43",
    "traceId": "1778329063622889474"
}

For Business Inquiries and Discounts, Please Contact

Manager Liao: +86-18758246772, liaowenguo@dubbingx.com

Manager Huang: +86-13091911143, huangbai@dubbingx.com

Manager Peirong: +86-13645716337, huangpeirong@dubbingx.com