All Products
Search

This Product

    Intelligent Media Services:SubmitIProductionJob

    Document Center

    Intelligent Media Services:SubmitIProductionJob

    Last Updated:Aug 05, 2026

    Submits an intelligent production job by calling SubmitIProductionJob.

    Operation description

    This is an asynchronous operation. After you submit a job, a job ID is returned. The job is not yet complete at this point and enters a background queue for asynchronous execution. The final result is delivered through a callback notification. You can also proactively query the job status by calling QueryIProductionJob.

    Try it now

    Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

    Test

    RAM authorization

    The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

    • Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.

    • API: The API that you can call to perform the action.

    • Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.

    • Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.

      • For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.

      • For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.

    • Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.

    • Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

    Action

    Access level

    Resource type

    Condition key

    Dependent action

    ice:SubmitIProductionJob

    create

    *All Resource

    *

    		 None None

    Request parameters

    Parameter

    Type

    Required

    Description

    Example
    Name

    string

    No

    The job name. The name can be up to 100 characters in length.

    Test task
    FunctionName

    string

    Yes

    The name of the algorithm function to use. Valid values:

    • Cover: intelligent cover

    • VideoClip: video synopsis

    • VideoDelogo: video logo removal

    • VideoDetext: video subtitle removal

    • CaptionExtraction: caption extraction

    • VideoGreenScreenMatting: image matting

    • FaceBeauty: video face beautification

    • VideoH2V: intelligent landscape-to-portrait

    • MusicSegmentDetect: chorus detection

    • AudioBeatDetection: beat detection

    • AudioQualityAssessment: audio quality assessment

    • SpeechDenoise: speech denoising

    • AudioMixing: audio mixing

    • MusicDemix: vocal and accompaniment separation

    Cover
    Input

    object

    Yes

    The input media. Object Storage Service (OSS) paths and media asset IDs are supported.

    Different algorithm functions have different input file requirements. For more information, see the supplementary description below.

    Type

    string

    Yes

    The media type. Valid values:

    • OSS: an OSS path

    • Media: a media asset ID

    OSS
    Media

    string

    Yes

    The input media. OSS paths and media asset IDs are supported. OSS path rules (use either format):

    1. oss://bucket/object

    2. http(s)://bucket.oss-[regionId].aliyuncs.com/object where bucket is the name of an OSS bucket in the same region as the current project, and object is the file path.

    oss://bucket/object
    Output

    object

    Yes

    The output media. OSS paths and media asset IDs are supported.

    Different algorithm functions produce different output files. For more information, see the supplementary description below.

    Type

    string

    Yes

    The media type. Valid values:

    • OSS: an OSS path

    • Media: a media asset ID

    OSS
    Biz

    string

    No

    The business type to which the media asset belongs.

    IMS
    Media

    string

    Yes

    The output media. If Type is set to OSS, specify an OSS path. If Type is set to Media, specify a media asset ID.

    OSS path rules (use either format):

    1. oss://bucket/object

    2. http(s)://bucket.oss-[RegionId].aliyuncs.com/object where bucket is the name of an OSS bucket in the same region as the current project, and object is the file path.

    Media asset ID:

    • You can specify an existing MediaId.

      • You do not need to specify Biz. The value follows the source.

    • You can create a new MediaId (leave MediaId empty).

      • The Biz value determines whether the media asset is written to IMS or VOD. If Biz is not specified, the value follows the source or defaults to IMS.

    Note

    The OSS path supports placeholders, such as oss://example-****/iproduction/{source}-{timestamp}-{sequenceId}.png. The following placeholders are supported:

    • {source}: populated with the input file name

    • {timestamp}: populated with the UNIX timestamp

    • {sequenceId}: populated with the generation sequence number

    • {resultType}: populated with the output file type (determined by the server) Placeholders are not required. However, for algorithms with multiple outputs, such as intelligent cover, include the sequence number placeholder to ensure unique output file paths.

    oss://bucket/object
    OutputUrl

    string

    No

    The OSS path of the output file when Type is set to Media. The bucket must be registered in IMS or VOD.

    http(s)://bucket.oss-[RegionId].aliyuncs.com/object
    TemplateId

    string

    No

    The template ID.

    ****20b48fb04483915d4f2cd8ac****
    JobParams

    string

    No

    The algorithm job parameters. This is a JSON object. The parameters vary depending on the algorithm. For more information, see the supplementary description.

    {"Model":"gif"}
    ScheduleConfig

    object

    No

    The job scheduling configuration.

    PipelineId

    string

    No

    The pipeline ID.

    5246b8d12a62433ab77845074039c3dc
    Priority

    integer

    No

    The priority. Valid values: 1 to 10. A smaller value indicates a higher priority.

    6
    UserData

    string

    No

    The custom user data, which is returned as-is when you retrieve the result. The value can be up to 256 characters in length.

    {"test":1}
    ModelId

    string

    No

    The algorithm model ID. If this parameter is left empty, the default model for the corresponding function is used. In most cases, leave this parameter empty to use the default model.

    The following algorithm functions have non-default models available:

    • VideoDetext

      • ModelId = algo-video-detext-new: a subtitle removal algorithm with better results but slower speed and higher cost than the default algorithm.

    Input and Output field description.

    Cover

    Input: a video file. Output: several images (3 by default, distinguished by placeholders) in PNG or GIF format (depending on the JobParams parameter, which determines whether static or animated images are generated).

    VideoDelogo

    Input: a video file. Output: a video with logos removed (in MP4 format).

    VideoDetext

    Input: a video file. Output: a video with subtitles removed (in MP4 format).

    CaptionExtraction

    Input: a video file. Output: a subtitle file (in SRT format).

    VideoGreenScreenMatting

    Input: a video file. Output: a video after image matting (in MP4 or WebM format, depending on the JobParams parameter).

    FaceBeauty

    Input: a video file. Output: a video with face beautification applied (in MP4 format).

    VideoH2V

    Input: a video file. Output: a landscape-to-portrait video (in MP4 format).

    MusicSegmentDetect

    Input: an audio file. Output: a result file containing chorus detection information (in JSON format).

    AudioBeatDetection

    Input: an audio file. Output: a result file containing beat detection information (in JSON format).

    AudioQualityAssessment

    Input: an audio file. No output file is generated. The audio quality assessment result is returned directly in QueryIProductionJob.

    SpeechDenoise

    Input: an audio file. Output: a denoised audio file (in WAV format).

    AudioMixing

    Input: an audio file to be mixed. Output: a mixed audio file (in WAV format). For information about how to specify the audio file to be mixed in, see the JobParams parameters below.

    MusicDemix

    Input: an audio file (a song). Output: two audio files after vocal and accompaniment separation. Include the {resultType} placeholder in the Output path to distinguish between the vocal track and the background track.

    JobParams JSON field description.

    Cover

    • Model: String. The intelligent cover model. If left empty, image covers are generated. If set to gif, animated covers are generated.

    VideoDelogo

    • LogoModel: String. The type of logo to remove. Valid values: tv (general logo - TV station), internet (general logo - online media). Multiple values can be specified, separated by commas.

    • Boxes: String. The position of the target logo box, specified as normalized distances from the top-left corner: [xmin, ymin, width, height]. Up to two target logo boxes are supported. Example: "[[0, 0, 0.3, 0.3], [0.7, 0, 0.3, 0.3]]".

    VideoDetext

    • LimitRegion: List. The restricted subtitle detection region, specified as normalized distances from the top-left corner: [xmin, ymin, width, height]. Multiple detection regions are supported. Example: [[0, 0, 0.3, 0.3], [0.7, 0, 0.3, 0.3]]. If this parameter is not set, the default detection region is the bottom 30% of the video.

    • Time: The global erasure time range (in seconds). List type, including the start time and end time: [start_time, end_time]. Example: [5, 20], which means only subtitles between 5 and 20 seconds of the video are erased.

      • The Time parameter can be a one-dimensional array, such as [5, 20], to specify a single time range.

      • The Time parameter can also be a two-dimensional array, such as [[5, 20], [25, 43], [51, 80]], to specify multiple time ranges (supported only when modelId=algo-video-detext-new).

    CaptionExtraction

    • fps: The sampling frame rate (optional). Integer. Valid values: 2 to 10. Default value: 5.

    • roi: The subtitle selection region (only subtitles within this region are extracted). Format: [[top, bottom], [left, right]], with normalized values (for example, the bottom half: [[0.5, 1], [0, 1]]). If this parameter is not specified, the bottom 1/4 of the video is used by default.

    • lang: The recognition language. Valid values: ch (Chinese), en (English), ch_ml (Chinese-English mixed). Default value: ch.

    • track: If set to "main", only the main subtitle track is extracted. If not specified, all subtitles within the region are extracted by default.

    VideoGreenScreenMatting

    • bgimage: The background image to overlay after matting. Example: http://example-image-****.example-location.aliyuncs.com/example/example.jpg. If this parameter is not specified, a WebM video with a transparent channel is output.

    FaceBeauty

    • beauty_params: The face beautification parameters. Example: "whiten=20,smooth=50,face_thin=50". For more information, see Parameter field description.

    VideoH2V

    None.

    MusicSegmentDetect

    None.

    AudioBeatDetection

    None.

    AudioQualityAssessment

    None.

    SpeechDenoise

    Input audio requirements: the format must be WAV, and the sample rate must be 16 kHz or 48 kHz.

    AudioMixing

    • inputs: The list of audio track file URLs to be mixed. Only one file is supported. Example: {"file":"http://example-bucket-****.oss-ap-southeast-1.aliyuncs.com/2.mp4"}

    MusicDemix

    None.

    Response elements

    Element

    Type

    Description

    Example

    object

    Schema of Response

    RequestId

    string

    The request ID.

    C1849434-FC47-5DC1-92B6-F7EAAFE3851E
    JobId

    string

    The intelligent production job ID.

    ****20b48fb04483915d4f2cd8ac****

    Examples

    Success response

    JSON format

    {
  "RequestId": "C1849434-FC47-5DC1-92B6-F7EAAFE3851E",
  "JobId": "****20b48fb04483915d4f2cd8ac****"
}

    Error codes

    See Error Codes for a complete list.

    Release notes

    See Release Notes for a complete list.