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

# Music Cover

> Create an AI voice cover of a song by replacing the original vocals with a target AI voice model.



## OpenAPI

````yaml POST /v1/music/cover
openapi: 3.0.1
info:
  title: FineVoice API
  description: >-
    This is the documentation for the FineVoice API. If you have any questions
    or need assistance, please contact support@finevoice.ai.
  version: v1
servers:
  - url: https://apis.finevoice.ai
    description: FineVoice API Gateway
security:
  - BearerAuth: []
paths:
  /v1/music/cover:
    post:
      tags:
        - Music
      summary: Music Cover
      description: >-
        Create an AI voice cover of a song by replacing the original vocals with
        a target AI voice model.
      operationId: MusicCover
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MusicCoverRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                type: object
        '401':
          description: Unauthorized — invalid or missing API key.
        '422':
          description: Validation error — check request body fields.
components:
  schemas:
    MusicCoverRequest:
      type: object
      description: The music cover request payload.
      properties:
        voice:
          type: string
          description: The primary target voice model name.
          example: james
        pitch:
          type: number
          format: float
          minimum: -12
          maximum: 12
          description: Vocal pitch offset in semitones.
          example: 0
          default: 0
        outputFormat:
          type: string
          description: The desired output format.
          example: mp3
        audioName:
          type: string
          description: The output audio name.
        audioCover:
          type: string
          description: The cover image URL.
        way:
          type: string
          description: Processing mode. Must be `m2`.
          example: m2
        cut:
          type: integer
          format: int32
          description: The cut mode.
        engine:
          type: string
          description: >-
            Voice conversion engine. `v5`: great for singing (rich vibrato, more
            noise). `v7`: great for speech (clean, stable).
          example: v5
          enum:
            - v5
            - v7
        sourceUrl:
          type: string
          description: The source audio URL.
          example: https://example.com/song.mp3
        singers:
          type: array
          items:
            $ref: '#/components/schemas/MusicCoverSingerRequest'
          description: Singer configurations for a multi-singer cover.
        instrument_pitch:
          type: number
          format: float
          description: Instrumental pitch offset in semitones.
        pitch_control:
          type: string
          description: Pitch control mode. Must be `rmvpe`.
          example: rmvpe
        diffusion_steps:
          type: integer
          format: int32
          description: Number of diffusion steps.
        auto_f0_adjust:
          type: boolean
          description: Whether to enable automatic F0 adjustment.
        vocal_types:
          type: string
          description: Vocal type configuration.
          example: solo
          default: solo
          enum:
            - solo
            - chorus
            - duets
    MusicCoverSingerRequest:
      type: object
      description: A singer configuration for a multi-singer music cover task.
      properties:
        voice:
          type: string
          description: The singer voice model name.
          example: james
        pitch:
          type: number
          format: float
          description: Pitch offset for this singer in semitones.
        engine:
          type: string
          description: >-
            Voice conversion engine. `v5`: great for singing. `v7`: great for
            speech.
          example: v5
          enum:
            - v5
            - v7
        diffusion_steps:
          type: integer
          format: int32
          description: Number of diffusion steps.
        auto_f0_adjust:
          type: boolean
          description: Whether to enable automatic F0 adjustment.
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: 'Bearer token (API key). Format: `Bearer {your_api_key}`'

````