Skip to main content
POST
/
tasks
Create Task
curl --request POST \
  --url https://api.audioshake.ai/tasks \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "assetId": "your_asset_id",
  "targets": [
    {
      "model": "vocals",
      "formats": [
        "wav"
      ]
    },
    {
      "model": "instrumental",
      "formats": [
        "wav"
      ]
    }
  ]
}
'
{
  "id": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "completedAt": "2023-11-07T05:31:56Z",
  "clientId": "<string>",
  "cost": 123,
  "assetId": "<string>",
  "url": "<string>",
  "metadata": "<string>",
  "targets": [
    {
      "id": "<string>",
      "model": "<string>",
      "formats": [
        "<string>"
      ],
      "output": [
        {
          "name": "<string>",
          "format": "<string>",
          "link": "<string>"
        }
      ],
      "cost": 123,
      "error": {
        "code": 123,
        "message": "<string>"
      },
      "duration": 123,
      "residual": true,
      "language": "<string>",
      "transcriptUrl": "<string>",
      "transcriptAssetId": "<string>"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://developer.audioshake.ai/llms.txt

Use this file to discover all available pages before exploring further.

Submit a media source and up to 20 model targets for processing. Each target specifies a model and output format. Provide exactly one source — either a public url or an assetId from a previous upload.

​
Examples

Separate vocals and instrumental: 
{
  "assetId": "your_asset_id",
  "targets": [
    { "model": "vocals", "formats": ["wav"] },
    { "model": "instrumental", "formats": ["wav"] }
  ]
}
Transcribe lyrics: 
{
  "assetId": "your_asset_id",
  "targets": [
    { "model": "transcription", "formats": ["json"] }
  ]
}

​
Checking results

Tasks process asynchronously. The response returns a Task id you can use to check progress:
1

Task is created

Each target begins in processing status.
2

Check for completion

Call Get Task by ID and check each target’s status. When a target finishes, its status becomes completed (with output download links) or error.
Use webhooks to get notified when a Task completes instead of polling.

Authorizations

​
x-api-key
string
header
required

Body

application/json
​
assetId
string
required

Asset ID of an input media file

​
targets
object[]
required

One or more model targets to process

Required array length: 1 - 20 elements
​
metadata
string

Client-provided metadata. Stored and returned as-is in responses and webhooks.

Maximum string length: 4096

Response

200 - application/json

Default Response

​
id
string

Unique identifier of the Task

​
createdAt
string<date-time>

Timestamp of when the Task was created

​
completedAt
string<date-time> | null

Timestamp of when the Task was completed

​
clientId
string

Unique identifier of the client

​
cost
number

Processing cost in credits

​
assetId
string

Asset ID of an input media file. Mutually exclusive with url

​
url
string | null

URL of an input media file. Mutually exclusive with assetId

​
metadata
string

Client-provided metadata. Stored and returned as-is in responses and webhooks.

​
targets
object[]

Processing targets and their current status