> ## 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.

# Get Stems

> Separate audio into individual stems

Separate an audio track into individual stems (vocals, drums, bass, etc.). Useful for remixing, karaoke creation, or isolating specific elements.

<Info>
  This is an async task. The response contains a `taskId` — use [Get Task Status](/api-reference/producer/task) to poll for the stem download URLs.
</Info>


## OpenAPI

````yaml POST /producer/stems
openapi: 3.0.0
info:
  title: Producer - AI Music Generation
  description: >-
    Generate music with Google DeepMind's Lyria 3 Pro model. Supports
    text-to-music, lyrics-to-music, and image-guided generation with stem
    separation and multi-format export.
  version: 2.0.0
  contact: {}
servers:
  - url: https://api.mountsea.ai
    description: API Gateway
security: []
tags:
  - name: producer
    description: >-
      Music generation, audio upload, stem separation, and export endpoints
      powered by Lyria 3 Pro
paths:
  /producer/stems:
    post:
      tags:
        - producer
      summary: 获取音轨分离
      description: 获取已生成音频的音轨分离文件。返回 taskId，使用 /producer/tasks 接口轮询获取结果
      operationId: ApiPublicController_getStems
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GetStemsDto'
      responses:
        '200':
          description: 任务创建成功
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskIdDto'
        '201':
          description: ''
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskIdDto'
      security:
        - bearerAuth: []
components:
  schemas:
    GetStemsDto:
      type: object
      properties:
        audioId:
          type: string
          description: 音频 ID
      required:
        - audioId
    TaskIdDto:
      type: object
      properties:
        taskId:
          type: string
          description: 任务 ID，用于后续查询结果
      required:
        - taskId
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT

````