> ## 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.

# Stem Separation

> Separate audio into individual stems

Separate audio into individual stems using ElevenLabs' stem separation technology.

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

## Separation Modes

| Mode           | Description                      | Cost                 |
| -------------- | -------------------------------- | -------------------- |
| `two_stems_v1` | Vocals + Instrumental (2 tracks) | 0.5x generation cost |
| `six_stems_v1` | 6 individual stems (default)     | 1x generation cost   |

<Tip>
  Use `two_stems_v1` for simple vocal/instrumental separation at half the cost. Use `six_stems_v1` when you need granular control over individual instruments.
</Tip>


## OpenAPI

````yaml POST /eleven/stems
openapi: 3.0.0
info:
  title: Eleven AI
  description: API documentation for Eleven AI
  version: 1.0.0
  contact: {}
servers:
  - url: https://api.mountsea.ai
    description: API Gateway
security: []
tags:
  - name: eleven
    description: ''
paths:
  /eleven/stems:
    post:
      tags:
        - eleven
      summary: 音轨分离
      description: |-
        对应 ElevenLabs POST /v1/music/separate-stems。
        将音频分离为不同音轨。返回 taskId，使用 GET /eleven/tasks 轮询获取结果
      operationId: ApiPublicController_separateStems
      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'
      security:
        - bearerAuth: []
components:
  schemas:
    GetStemsDto:
      type: object
      properties:
        audioUrl:
          type: string
          description: 要分离的音频文件 URL（服务端会先下载再上传至 ElevenLabs）
          example: https://example.com/song.mp3
        stemVariationId:
          enum:
            - two_stems_v1
            - six_stems_v1
          type: string
          description: >-
            音轨分离变体。two_stems_v1 = 人声+伴奏双轨（0.5× 生成费用），six_stems_v1 = 六轨分离（1×
            生成费用）
          default: six_stems_v1
        outputFormat:
          enum:
            - mp3_22050_32
            - mp3_24000_48
            - mp3_44100_32
            - mp3_44100_64
            - mp3_44100_96
            - mp3_44100_128
            - mp3_44100_192
            - pcm_8000
            - pcm_16000
            - pcm_22050
            - pcm_24000
            - pcm_32000
            - pcm_44100
            - pcm_48000
            - ulaw_8000
            - alaw_8000
            - opus_48000_32
            - opus_48000_64
            - opus_48000_96
            - opus_48000_128
            - opus_48000_192
          type: string
          description: 各音轨的输出格式，格式为 codec_sampleRate_bitrate
          default: mp3_44100_128
        signWithC2pa:
          type: boolean
          description: 是否使用 C2PA 签名标记 AI 生成内容。仅适用于 MP3 输出格式
          default: false
      required:
        - audioUrl
    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

````