tencent cloud

APIs

CreateAIRecognitionTemplate

Download
Focus Mode
Font Size
Last updated: 2026-09-18 16:50:19

1. API Description

Domain name for API request: vod.intl.tencentcloudapi.com.

This API is used to create a user-defined audio and video content recognition template. Maximum quantity: 50.

A maximum of 10 requests can be initiated per second for this API.

We recommend you to use API Explorer
Try it
API Explorer provides a range of capabilities, including online call, signature authentication, SDK code generation, and API quick search. It enables you to view the request, response, and auto-generated examples.

2. Input Parameters

The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.

Parameter Name Required Type Description
Action Yes String Common Params. The value used for this API: CreateAIRecognitionTemplate.
Version Yes String Common Params. The value used for this API: 2018-07-17.
Region No String Common Params. This parameter is not required.
SubAppId No Integer VOD application ID. For customers who activate VOD services after December 25, 2023, this field must be set to the app ID when accessing resources in VOD applications (whether the default application or a newly created application).
Name No String Video content recognition template name. Length limit: 64 characters.
Comment No String Description of the audio/video content recognition template, with a length limit of 256 characters.
HeadTailConfigure No HeadTailConfigureInfo Control parameters for video opening and closing recognition.
SegmentConfigure No SegmentConfigureInfo Video split recognition control parameters.
FaceConfigure No FaceConfigureInfo Control parameters for face recognition.
OcrFullTextConfigure No OcrFullTextConfigureInfo Text Full-text Recognition Control Parameters.
OcrWordsConfigure No OcrWordsConfigureInfo Text keyword recognition control parameters.
AsrFullTextConfigure No AsrFullTextConfigureInfo Voice full-text recognition control parameters.
Note: This parameter is no longer maintained. It is recommended to use the AsrTranslateConfigure parameter to initiate speech translation recognition (when DstLanguage is not filled in or is an empty string, no translation is performed, and the billing item is the same as full text speech recognition).
AsrWordsConfigure No AsrWordsConfigureInfo Voice keyword recognition control parameters.
AsrTranslateConfigure No AsrTranslateConfigureInfo Speech translation recognition control parameters.
ObjectConfigure No ObjectConfigureInfo Control parameters for object recognition.
ScreenshotInterval No Float Frame interception interval in seconds. If not specified, the default frame interval is 1 second, with a minimum value of 0.5 seconds.

3. Output Parameters

Parameter Name Type Description
Definition Integer Unique ID of the audio/video content recognition template.
RequestId String The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem.

4. Example

Example1 Creating a Task Template That Only Supports Video Start and End Recognition

This example shows you how to create a customized audio and video content recognition template with only the video opening and closing credits recognition task enabled.

Input Example

POST / HTTP/1.1
Host: vod.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: CreateAIRecognitionTemplate
<Common request parameters>

{
    "Comment": "Template 1",
    "HeadTailConfigure": {
        "Switch": "ON"
    },
    "Name": "Video start and end recognition task template"
}

Output Example

{
    "Response": {
        "Definition": 30,
        "RequestId": "12ae8d8e-dce3-4151-9d4b-5594145287e1"
    }
}

Example2 Creating a Task Template That Only Supports Speech Translation

This example shows you how to create a customized audio and video content recognition template with only the voice translation task enabled.

Input Example

POST / HTTP/1.1
Host: vod.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: CreateAIRecognitionTemplate
<Common request parameters>

{
    "AsrTranslateConfigure": {
        "Switch": "ON",
        "SrcLanguage": "zh",
        "DstLanguage": "en",
        "SubtitleFormats": [
            "vtt"
        ]
    },
    "Name": "Speech Translation Template_Chinese to English"
}

Output Example

{
    "Response": {
        "Definition": 31,
        "RequestId": "0de23d47-ff58-41d7-80c4-c4fa7dbc6c21"
    }
}

Example3 Creating a Template for Multiple Recognition Tasks, with the Frame Extraction Interval Specified

This example shows you how to create a customized audio and video content recognition template with video splitting and face recognition enabled. The default and custom face libraries are used, the face recognition filter score is 90, and the frame interception interval is 1.0 seconds.

Input Example

POST / HTTP/1.1
Host: vod.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: CreateAIRecognitionTemplate
<Common request parameters>

{
"Comment": "Template 3",
    "FaceConfigure": {
        "Switch": "ON",
        "FaceLibrary": "All"
    },
    "ScreenshotInterval": 1.0,
"Name": "Intelligent Identification Template"
    "SegmentConfigure": {
        "Switch": "ON"
    }
}

Output Example

{
    "Response": {
        "Definition": 32,
        "RequestId": "12ae8d8e-dce3-4151-9d4b-5594145287e1"
    }
}

Example4 Creating a Template for Multiple Audio/Video Content Recognition Tasks

This example shows you how to create a customized audio and video content recognition template with video splitting and face recognition enabled. The default face library is used, and the face recognition filter score is 90.

Input Example

POST / HTTP/1.1
Host: vod.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: CreateAIRecognitionTemplate
<Common request parameters>

{
"Comment": "Template 2",
    "FaceConfigure": {
        "Switch": "ON",
        "Score": 90,
        "FaceLibrary": "Default"
    },
"Name": "Intelligent Identification Template"
    "SegmentConfigure": {
        "Switch": "ON"
    }
}

Output Example

{
    "Response": {
        "Definition": 31,
        "RequestId": "12ae8d8e-dce3-4151-9d4b-5594145287e1"
    }
}

5. Developer Resources

SDK

TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.

Command Line Interface

6. Error Code

The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.

Error Code Description
FailedOperation Operation failed.
InternalError Internal error.
InvalidParameter Parameter error.
InvalidParameterValue.Comment Parameter error: description of this template.
InvalidParameterValue.DefaultLibraryLabelSet Parameter value error: The default face library filter tag is illegal.
InvalidParameterValue.FaceLibrary Parameter value error: The face library parameter is invalid.
InvalidParameterValue.FaceScore Parameter value error: The face score parameter value is invalid.
InvalidParameterValue.LabelSet Incorrect parameter value: the LabelSet parameter value is invalid.
InvalidParameterValue.Name Parameter value error: Name exceeds the length limit.
InvalidParameterValue.ObjectLibrary Parameter value error: Invalid object library parameter.
InvalidParameterValue.ScreenshotInterval Incorrect parameter value: the ScreenshotInterval parameter value is invalid.
InvalidParameterValue.SubtitleFormat Parameter value error: Invalid SubtitleFormat parameter.
InvalidParameterValue.Switch Parameter value error: invalid Switch parameter value.
InvalidParameterValue.UserDefineLibraryLabelSet Parameter value error: The custom face library filter tag is illegal.
LimitExceeded.TooMuchTemplate Exceed the limit: The number of templates exceeds the upper limit of 100. If needed, submit a ticket (https://console.tencentcloud.com/workorder/category).
UnauthorizedOperation Unauthorized operation.

Help and Support

Was this page helpful?

Help us improve! Rate your documentation experience in 5 mins.

Feedback