> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apistable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Add an instrumental stem

> Add a selected instrumental part to existing audio. Receive the new part or wait for the mix.

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

## Using this operation

Add a selected instrumental part to existing audio. Receive the new part or wait for the mix.

* 1. Prepare the fields shown in the example below. Replace sample URLs and IDs with resources you can access.
* 2. Set model to suno\_add\_stem and place the parameters inside input. Submit once and save the returned task\_id.
* 3. Query the saved task or receive its callback. A processing result is not a reason to submit the operation again.
* Read songs from result.data.data. Each song has its own APIstable id, which can be used as audio\_id in a later task.

## 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.

```json theme={null}
{
  "model": "suno_add_stem",
  "input": {
    "audio_id": "YOUR_AUDIO_ID",
    "stem_prompt": "Piano"
  }
}
```

## 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.

```json theme={null}
{
  "code": 200,
  "msg": "success",
  "data": {
    "task_id": "YOUR_TASK_ID"
  }
}
```

## Parameter reference

| Field | Type | Required | Description and limits |
| - | - | - | - |
| 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\_prompt | string | Yes | PayAPI extension: describe the instrument or backing stem to add. maxLength: 1000 |
| model | string | No / conditional | Suno version: V6, V6\_MINI or V6\_WILD. Extension must match the generated source model. values: V6, V6\_MINI, V6\_WILD; default: V6 |
| title | string | No / conditional | Title. Generate/cover: up to 80 characters; extend and other operations: up to 100. Required for custom generation. maxLength: 100 |
| result\_mode | string | No / conditional | Extension/replacement: full\_song (default) or segment. Added stem: mixed (default) or stem. Full/mixed results wait for assembly. values: stem, mixed; default: mixed |

## 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.

```json theme={null}
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "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_prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1000,
      "description": "PayAPI extension: describe the instrument or backing stem to add."
    },
    "model": {
      "default": "V6",
      "type": "string",
      "enum": [
        "V6",
        "V6_MINI",
        "V6_WILD"
      ],
      "description": "Suno version: V6, V6_MINI or V6_WILD. Extension must match the generated source model."
    },
    "title": {
      "type": "string",
      "maxLength": 100,
      "description": "Title. Generate/cover: up to 80 characters; extend and other operations: up to 100. Required for custom generation."
    },
    "result_mode": {
      "default": "mixed",
      "type": "string",
      "enum": [
        "stem",
        "mixed"
      ],
      "description": "Extension/replacement: full_song (default) or segment. Added stem: mixed (default) or stem. Full/mixed results wait for assembly."
    }
  },
  "required": [
    "audio_id",
    "stem_prompt"
  ],
  "additionalProperties": false
}
```

## Important conditions

* full\_song/mixed results wait for assembly; segment/stem returns the requested part. An assembly failure is not reported as a complete song. Partial song success is identified by the result message.
* Song audio may be MP3 or M4A. Use suno\_export\_mp3 for an actual MP3 file. Unavailable optional cover art may be null; audio remains usable.
* 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.

```json theme={null}
{
  "type": "object",
  "required": [
    "code",
    "msg",
    "data"
  ],
  "properties": {
    "code": {
      "const": 200
    },
    "msg": {
      "type": "string"
    },
    "data": {
      "type": "object",
      "required": [
        "callbackType",
        "task_id",
        "data"
      ],
      "properties": {
        "callbackType": {
          "const": "complete"
        },
        "task_id": {
          "type": "string"
        },
        "data": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "id",
              "audio_url",
              "stream_audio_url",
              "image_url",
              "prompt",
              "lyrics",
              "model_name",
              "title",
              "createTime",
              "duration",
              "tags",
              "source_audio_url",
              "source_image_url",
              "source_stream_audio_url"
            ],
            "properties": {
              "id": {
                "type": "string"
              },
              "audio_url": {
                "type": "string"
              },
              "stream_audio_url": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "image_url": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "prompt": {
                "type": "string"
              },
              "lyrics": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "model_name": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "title": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "createTime": {
                "type": [
                  "integer",
                  "null"
                ]
              },
              "duration": {
                "type": [
                  "number",
                  "null"
                ]
              },
              "tags": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "source_audio_url": {
                "type": "string"
              },
              "source_image_url": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "source_stream_audio_url": {
                "type": [
                  "string",
                  "null"
                ]
              }
            }
          }
        }
      }
    }
  }
}
```

> Song duration is in seconds; task duration is in milliseconds. createTime is a Unix timestamp in milliseconds or null. Current stream\_audio\_url and source\_stream\_audio\_url are null. source\_audio\_url/source\_image\_url refer to the same APIstable-hosted copies as audio\_url/image\_url, not provider links. Process the actual song array; upload registration does not imply two newly generated songs.

## Related workflows

[Voice: all four steps](https://docs.apistable.ai/suno-voice-workflow.md) [File uploads](https://docs.apistable.ai/file-upload.md) [Callbacks](https://docs.apistable.ai/webhooks.md)


## OpenAPI

````yaml openapi-suno-add-stem.json POST /api/v1/tasks/create_task
openapi: 3.1.0
info:
  title: APIstable API
  version: 1.0.0-preview
  description: >-
    Public /api/v1 protocol. Valid API keys have the same account-scoped access.
    Read the selected model documentation for its ID, supported inputs, result
    format and availability before submitting. No client submission idempotency
    or max_credits. Availability, pricing, file retention and callback formats
    follow the selected model contract. Unconfigured operations return 503.
servers:
  - url: https://apistable.ai
    description: APIstable API
security: []
paths:
  /api/v1/tasks/create_task:
    post:
      summary: Add an instrumental stem
      description: >-
        Add a selected instrumental part to existing audio. Receive the new part
        or wait for the mix.
      operationId: suno_add_stem
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
              additionalProperties: false
              properties:
                model:
                  type: string
                  enum:
                    - suno_add_stem
                  example: suno_add_stem
                input:
                  $schema: https://json-schema.org/draft/2020-12/schema
                  type: object
                  properties:
                    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_prompt:
                      type: string
                      minLength: 1
                      maxLength: 1000
                      description: >-
                        PayAPI extension: describe the instrument or backing
                        stem to add.
                    model:
                      default: V6
                      type: string
                      enum:
                        - V6
                        - V6_MINI
                        - V6_WILD
                      description: >-
                        Suno version: V6, V6_MINI or V6_WILD. Extension must
                        match the generated source model.
                    title:
                      type: string
                      maxLength: 100
                      description: >-
                        Title. Generate/cover: up to 80 characters; extend and
                        other operations: up to 100. Required for custom
                        generation.
                    result_mode:
                      default: mixed
                      type: string
                      enum:
                        - stem
                        - mixed
                      description: >-
                        Extension/replacement: full_song (default) or segment.
                        Added stem: mixed (default) or stem. Full/mixed results
                        wait for assembly.
                  required:
                    - audio_id
                    - stem_prompt
                  additionalProperties: false
                callback_url:
                  type: string
                  format: uri
                  description: >-
                    Optional public HTTPS endpoint for signed completion
                    callbacks; no redirects or private IPs.
            example:
              model: suno_add_stem
              input:
                audio_id: YOUR_AUDIO_ID
                stem_prompt: Piano
      responses:
        '200':
          description: Accepted task. Poll the common task endpoint or use callback_url.
          content:
            application/json:
              schema:
                type: object
                required:
                  - code
                  - msg
                  - data
                additionalProperties: false
                properties:
                  code:
                    const: 200
                  msg:
                    const: success
                  data:
                    type: object
                    required:
                      - task_id
                    additionalProperties: false
                    properties:
                      task_id:
                        type: string
        '400':
          description: >-
            40001 invalid JSON, 40002 invalid input/callback, 40003 unsupported
            parameter.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Invalid or revoked API key.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '402':
          description: '40201: Insufficient credits (live acceptance).'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: '40401: Unknown model or resource not found in this account.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '409':
          description: '40901: Resource belongs to a different provider account.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '410':
          description: '41001: Source audio or temporary resource has expired.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: '41301: Request too large.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '422':
          description: '42201: Requested capability combination is not enabled.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: '42901: Rate/concurrency limit (live acceptance).'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '503':
          description: '50301: Service/provider unavailable. No live submission or charge.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      security:
        - bearerAuth: []
components:
  schemas:
    Error:
      type: object
      required:
        - code
        - msg
        - data
      properties:
        code:
          type: integer
        msg:
          type: string
        data:
          type: 'null'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Every valid key can submit and query its own account. Revoked keys are
        rejected.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.