SubmitAudioProduceJob

Updated at:

Converts the provided text content into high-quality speech audio files.

Operation description

This operation is an asynchronous operation. After a task is submitted, a task ID is returned. The task is not completed 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 task status by calling the Query intelligent task results operation.

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:SubmitAudioProduceJob

create

*All Resource

*

None None

Request parameters

Parameter

Type

Required

Description

Example

EditingConfig

string

Yes

The audio production configuration:

  • voice: The voice type.

  • customizedVoice: The VoiceId for voice cloning.

  • format: The output file format. Valid values: PCM, WAV, and MP3.

  • volume: The volume. Valid values: 0 to 100. Default value: 50.

  • speech_rate: The speech rate. Valid values: -500 to 500. Default value: 0.
    • [-500, 0, 500] corresponds to the speech rate multiplier range of [0.5, 1.0, 2.0].

    • The calculation method is as follows:
      • 0.8x speed: (1 - 1/0.8) / 0.002 = -125

      • 1.2x speed: (1 - 1/1.2) / 0.001 = 166

      • For speeds less than 1x, the 0.002 coefficient is used.

      • For speeds greater than 1x, the 0.001 coefficient is used.

  • pitch_rate: The pitch. Valid values: -500 to 500. Default value: 0.
    Important If both voice and customizedVoice are specified, customizedVoice takes precedence.

{"voice":"Siqi","format":"MP3","volume":50}

OutputConfig

string

Yes

The audio output configuration. For example, to store the output speech at http://my_bucket.oss-cn-shanghai.aliyuncs.com/target_audio.mp3, the parameter settings are as follows: { "bucket": "my_bucket", "object": "target_audio" }

{ "bucket": "my_bucket", "object": "target_audio" }

InputConfig

string

Yes

The text content. A maximum of 10,000 Chinese characters are supported. Speech Synthesis Markup Language (SSML) is supported.

test

Title

string

No

The task title. If not provided, a default title is automatically generated based on the date.

  • The length cannot exceed 128 bytes.

  • UTF-8 encoding.

taskTitle

Description

string

No

The task description:

  • The length cannot exceed 1,024 bytes.

  • UTF-8 encoding.

taskDescription

UserData

string

No

The custom settings in JSON format. The maximum length is 512 bytes. Custom callback URL configuration is supported.

{"NotifyAddress":"http://xx.xx.xxx"}

Overwrite

boolean

No

Specifies whether to overwrite existing OSS files.

true

Response elements

Element

Type

Description

Example

object

Schema of Response

RequestId

string

The request ID.

******11-DB8D-4A9A-875B-275798******

JobId

string

The task ID.

****20b48fb04483915d4f2cd8ac****

State

string

The task status. Valid values:

  • Created

  • Executing

  • Finished

  • Failed

Created

MediaId

string

The media asset ID.

****2bcbfcfa30fccb36f72dca22****

You can use the JobId of the intelligent speech task to query the detailed execution information of the task by calling the Query intelligent task results operation. When the task is executed successfully, the sample response returned by the Query intelligent task results operation is as follows.

Note

By default, AI_TTS segments sentences based on Chinese punctuation marks such as commas and periods.

{
  "RequestId": "******2D-443C-5043-B0E4-867070******",
  "JobId": "******042d5e4db6866f6289d1******",
  "State": "Finished",
  "SmartJobInfo": {
    "Title": "default_title_2022-01-21T06:15:07Z",
    "JobType": "TextToSpeech",
    "CreateTime": "2022-01-21T06:15:07Z",
    "ModifiedTime": "2022-01-21T06:15:07Z",
    "InputConfig": {
      "InputFile": "When it comes to Guo Degang, it can be said that he is red and purple now, and the ticket price is often very high, but he is robbed as soon as he starts. He also participates in various crosstalk variety shows to comment on the new performers."
    },
    "EditingConfig": "{\"format\":\"MP3\",\"pitch_rate\":0,\"sample_rate\":16000,\"speech_rate\":0,\"voice\":\"Siqi\",\"volume\":50}",
    "OutputConfig": {
      "Bucket": "your-bucket",
      "Object": "your-audio"
    }
  },
  "JobResult": {
    "MediaId": "******bf47c94e82b3b2014361******",
    "AiResult": "[{\"text\":\"When it comes to\",\"begin_time\":0,\"end_time\":846},{\"text\":\"it can be said that he is red and purple now\",\"begin_time\":846,\"end_time\":3386},{\"text\":\"and the ticket price is often very high\",\"begin_time\":3386,\"end_time\":4402},{\"text\":\"but he is robbed as soon as he starts\",\"begin_time\":4402,\"end_time\":6265},{\"text\":\"He also participates in various crosstalk variety shows to comment on the new performers.\",\"begin_time\":6265,\"end_time\":10330}]"
  }
}

Examples

Success response

JSON format

{
  "RequestId": "******11-DB8D-4A9A-875B-275798******",
  "JobId": "****20b48fb04483915d4f2cd8ac****",
  "State": "Created",
  "MediaId": "****2bcbfcfa30fccb36f72dca22****"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.