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

# Custom Model Upload

> Upload training audio for custom model

<Info>
  This is **Step 2** of the Custom Model workflow. You must complete [Step 1: Prepare](/api-reference/suno/customModelPrepare) first. See the [full workflow guide](/api-reference/suno/customModel).
</Info>

Upload one audio file per request. The task result contains clip info with an `id` field — collect these as `clipIds` for the [create step](/api-reference/suno/customModelCreate).

**You need at least 6 successful uploads** before proceeding to create.

<Tip>
  Multiple upload requests can run in parallel with the same `sessionId`. Each returns its own `taskId` for independent polling.
</Tip>


## OpenAPI

````yaml POST /suno/v2/customModel/upload
openapi: 3.0.0
info:
  title: Suno AI
  description: API documentation for Suno AI
  version: 1.0.0
  contact: {}
servers:
  - url: https://api.mountsea.ai
    description: API Gateway
security: []
tags:
  - name: suno
    description: ''
  - name: suno/studio
    description: Studio Song Editor（与 audio/crop|fade|reverse 独立）
paths:
  /suno/v2/customModel/upload:
    post:
      tags:
        - suno
      summary: upload audio for custom model
      description: >-
        Async upload — uses the same account bound in the prepare step. Returns
        taskId to poll via /status. On success, clip info (including id) is in
        task result.
      operationId: ApiPublicController_customModelUpload
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CustomModelUploadDto'
      responses:
        '201':
          description: ''
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskIdDto'
      security:
        - bearerAuth: []
components:
  schemas:
    CustomModelUploadDto:
      type: object
      properties:
        sessionId:
          type: string
          format: uuid
          description: prepare 返回的会话 sessionId
        audioUrl:
          type: string
          format: uri
          description: 要上传的音频 URL（可下载的公网地址）
          example: https://example.com/song.mp3
      required:
        - sessionId
        - audioUrl
    TaskIdDto:
      type: object
      properties:
        taskId:
          type: string
          description: task id. Use this id to query task status.
          example: 15c257ff-43f7-4678-bd41-202ad6b8488b
      required:
        - taskId
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT

````