Vocal remover and stems

curl --request POST \
  --url https://apistable.com/api/v1/tasks/create_task \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "suno_separate_vocals",
  "input": {
    "type": "separate_vocal",
    "upload_url": "https://example.com/song.mp3"
  }
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'suno_separate_vocals',
    input: {type: 'separate_vocal', upload_url: 'https://example.com/song.mp3'}
  })
};

fetch('https://apistable.com/api/v1/tasks/create_task', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://apistable.com/api/v1/tasks/create_task"

payload = {
    "model": "suno_separate_vocals",
    "input": {
        "type": "separate_vocal",
        "upload_url": "https://example.com/song.mp3"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "<string>"
  }
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

POST

api

tasks

create_task

Vocal remover and stems

curl --request POST \
  --url https://apistable.com/api/v1/tasks/create_task \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "suno_separate_vocals",
  "input": {
    "type": "separate_vocal",
    "upload_url": "https://example.com/song.mp3"
  }
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'suno_separate_vocals',
    input: {type: 'separate_vocal', upload_url: 'https://example.com/song.mp3'}
  })
};

fetch('https://apistable.com/api/v1/tasks/create_task', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://apistable.com/api/v1/tasks/create_task"

payload = {
    "model": "suno_separate_vocals",
    "input": {
        "type": "separate_vocal",
        "upload_url": "https://example.com/song.mp3"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "<string>"
  }
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

{
  "code": 123,
  "msg": "<string>",
  "data": null
}

Operations are enabled individually by server configuration. Disabled operations return 503 without a task. Music credit deduction is currently disabled.

Using this operation

Use an audio URL for toolbox separation or an APIstable audio ID for native stems, then listen to and download individual parts.

1. Prepare the fields shown in the example below. Replace sample URLs and IDs with resources you can access.
1. Set model to suno_separate_vocals and place the parameters inside input. Submit once and save the returned task_id.
1. Query the saved task or receive its callback. A processing result is not a reason to submit the operation again.
Iterate result.stems to access each part’s download_url and expiry. Use the returned stem names and count.

Create task

Send model and input to the common task endpoint. callback_url is an optional top-level public HTTPS address. All resource IDs are APIstable IDs owned by your account. Music credit deduction is currently disabled.

{
  "model": "suno_separate_vocals",
  "input": {
    "type": "separate_vocal",
    "upload_url": "https://example.com/song.mp3"
  }
}

Acceptance response

HTTP 200 confirms acceptance, not completion. Query GET /api/v1/tasks/{task_id} until data.status is succeeded or failed. Read data.result only after success; a failed task has its error in data.message.

{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "YOUR_TASK_ID"
  }
}

Fields: type = separate_vocal

Field	Type	Required	Description and limits
type	string	Yes	separate_vocal (2 tracks), split_stem (4/6), or native split_stem_advanced. = separate_vocal
upload_url	string	Yes	Public HTTPS audio URL on port 443, without URL credentials. Use MP3/WAV/FLAC/OGG/M4A/AAC with a readable audio track. See the operation size limit.
output_format	string	No / conditional	Toolbox output: mp3, wav (default), flac, ogg, m4a or aac. Not accepted for native stem extraction. values: mp3, wav, flac, ogg, m4a, aac; default: wav

Fields: type = split_stem

Field	Type	Required	Description and limits
type	string	Yes	separate_vocal (2 tracks), split_stem (4/6), or native split_stem_advanced. = split_stem
upload_url	string	Yes	Public HTTPS audio URL on port 443, without URL credentials. Use MP3/WAV/FLAC/OGG/M4A/AAC with a readable audio track. See the operation size limit.
stem_mode	number	Yes	Toolbox separation: 4 or 6 stems. Vocal remover fixes this to 2 internally. values: 4, 6
output_format	string	No / conditional	Toolbox output: mp3, wav (default), flac, ogg, m4a or aac. Not accepted for native stem extraction. values: mp3, wav, flac, ogg, m4a, aac; default: wav

Fields: type = split_stem_advanced

Field	Type	Required	Description and limits
type	string	Yes	separate_vocal (2 tracks), split_stem (4/6), or native split_stem_advanced. = split_stem_advanced
audio_id	string	Yes	APIstable song ID belonging to your account. Cover/extend accept this ID only, without a source task_id or external URL. maxLength: 200
stem_name	string	No / conditional	Native extraction name. Only Piano is documented and enabled; omit for twelve-stem separation. maxLength: 100

Inputs and limits

The schema lists supported fields, types and basic limits. Also follow Important conditions: cross-field and source-resource checks are not fully represented in JSON Schema. Unknown parameters are rejected. URL fields accept public HTTPS URLs, never file objects.

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "oneOf": [
    {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "const": "separate_vocal",
          "description": "separate_vocal (2 tracks), split_stem (4/6), or native split_stem_advanced."
        },
        "upload_url": {
          "type": "string",
          "format": "uri",
          "description": "Public HTTPS audio URL on port 443, without URL credentials. Use MP3/WAV/FLAC/OGG/M4A/AAC with a readable audio track. See the operation size limit."
        },
        "output_format": {
          "default": "wav",
          "type": "string",
          "enum": [
            "mp3",
            "wav",
            "flac",
            "ogg",
            "m4a",
            "aac"
          ],
          "description": "Toolbox output: mp3, wav (default), flac, ogg, m4a or aac. Not accepted for native stem extraction."
        }
      },
      "required": [
        "type",
        "upload_url"
      ],
      "additionalProperties": false
    },
    {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "const": "split_stem",
          "description": "separate_vocal (2 tracks), split_stem (4/6), or native split_stem_advanced."
        },
        "upload_url": {
          "type": "string",
          "format": "uri",
          "description": "Public HTTPS audio URL on port 443, without URL credentials. Use MP3/WAV/FLAC/OGG/M4A/AAC with a readable audio track. See the operation size limit."
        },
        "stem_mode": {
          "anyOf": [
            {
              "type": "number",
              "const": 4
            },
            {
              "type": "number",
              "const": 6
            }
          ],
          "description": "Toolbox separation: 4 or 6 stems. Vocal remover fixes this to 2 internally."
        },
        "output_format": {
          "default": "wav",
          "type": "string",
          "enum": [
            "mp3",
            "wav",
            "flac",
            "ogg",
            "m4a",
            "aac"
          ],
          "description": "Toolbox output: mp3, wav (default), flac, ogg, m4a or aac. Not accepted for native stem extraction."
        }
      },
      "required": [
        "type",
        "upload_url",
        "stem_mode"
      ],
      "additionalProperties": false
    },
    {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "const": "split_stem_advanced",
          "description": "separate_vocal (2 tracks), split_stem (4/6), or native split_stem_advanced."
        },
        "audio_id": {
          "type": "string",
          "minLength": 1,
          "maxLength": 200,
          "description": "APIstable song ID belonging to your account. Cover/extend accept this ID only, without a source task_id or external URL."
        },
        "stem_name": {
          "type": "string",
          "minLength": 1,
          "maxLength": 100,
          "description": "Native extraction name. Only Piano is documented and enabled; omit for twelve-stem separation."
        }
      },
      "required": [
        "type",
        "audio_id"
      ],
      "additionalProperties": false
    }
  ]
}

Important conditions

separate_vocal and split_stem use upload_url with an audio limit of 100 MiB. separate_vocal requests two stems; split_stem requires stem_mode=4 or 6. Choose the documented output_format; default wav.
Native split_stem_advanced uses audio_id, not upload_url or output_format. Omit stem_name for twelve-stem separation, or pass Piano for the enabled single-stem extraction. Other names return 42201. Multiple groups may be returned; use the actual stems array rather than a fixed count.
Audio URL inputs must contain readable MP3/WAV/FLAC/OGG/M4A/AAC audio with positive duration; the limit is 100 MiB per file. URLs must be publicly accessible HTTPS on port 443, without embedded credentials or private-network addresses. Keep them accessible until the task finishes.
Uploaded files last 24 hours, generated files 14 days and task details 30 days. Reused files keep their original expiry. Valid Voice/Persona identity mappings are separate from task-log cleanup. Download files you need to retain.

Result schema

The creation response is {code:200,msg:“success”,data:{task_id}}. Poll GET /api/v1/tasks/{task_id}. On success, data.result is an object matching the schema below; it is otherwise null. input remains a JSON string.

{
  "type": "object",
  "required": [
    "stems"
  ],
  "properties": {
    "stems": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "stem_name": {
            "type": [
              "string",
              "null"
            ]
          },
          "download_url": {
            "type": "string"
          },
          "expires_at": {
            "type": "string"
          }
        }
      }
    }
  },
  "additionalProperties": false
}

Voice: all four steps File uploads Callbacks

Authorizations

Authorization

string

header

required

Every valid key can submit and query its own account. Revoked keys are rejected.

Body

application/json

model

enum<string>

required

Available options:

suno_separate_vocals

Example:

"suno_separate_vocals"

input

object

required

Option 1
Option 2
Option 3

Show child attributes

callback_url

string<uri>

Optional public HTTPS endpoint for signed completion callbacks; no redirects or private IPs.

Response

Accepted task. Poll the common task endpoint or use callback_url.

code

any

required

msg

any

required

data

object

required

Show child attributes

Getting started with APIstable

Market

Vocal remover and stems

Using this operation

Create task

Acceptance response

Fields: type = separate_vocal

Fields: type = split_stem

Fields: type = split_stem_advanced

Inputs and limits

Important conditions

Result schema

Authorizations

Body

Response

​Using this operation

​Create task

​Acceptance response

​Fields: type = separate_vocal

​Fields: type = split_stem

​Fields: type = split_stem_advanced

​Inputs and limits

​Important conditions

​Result schema

​Related workflows

Authorizations

Body

Response

Using this operation

Create task

Acceptance response

Fields: type = separate_vocal

Fields: type = split_stem

Fields: type = split_stem_advanced

Inputs and limits

Important conditions

Result schema

Related workflows