LALAL.AI Voice Change API

openapi: 3.1.0
info:
  title: LALAL.AI Batch Stem Separation Voice Change API
  version: 1.1.0
  description: '

    This is the LALAL.AI API.


    To authenticate, provide your license key in the `X-License-Key` header of each request.


    Typical usage example:

    1) Upload a file using the ''/upload/'' endpoint to get a ''source_id''.

    2) Start a splitting task using the ''/split/'' endpoint with the obtained ''source_id'' and desired presets.

    3) Check the status of your task using the ''/check/'' endpoint with the returned ''task_id''.

    4) Once the task is complete, download the processed files using urls from the ''/check/'' response.

    5) (If needed), you can delete the source file and all its resulting tracks from our servers, using the ''/delete/'' endpoint with the ''source_id''.


    Notes:


    You can use the same source_id for concurrent splitting tasks.


    You can check multiple task IDs in a single ''/check/'' request by providing a list of ''task_ids''.


    '
servers:
- url: https://www.lalal.ai
  description: LALAL.AI API v1 production endpoint
tags:
- name: Voice Change
paths:
  /api/v1/change_voice/:
    post:
      operationId: change_voice_change_voice
      summary: Changes voice in the audio file using voice pack
      parameters: []
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                anyOf:
                - $ref: '#/components/schemas/ApiV1ErrorResponse'
                - $ref: '#/components/schemas/CommonErrorResponse'
                title: Response
        '422':
          description: Unprocessable Entity
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CommonErrorResponse'
      description: "\n    For 'voice_pack_id' parameter use 'pack_id' from /voice_packs/list/ endpoint or one of legal packs: ['ALEX_KAYE', 'STASIA_FAYE', 'NICOLAAS_HAAS', 'NIK_ZEL', 'OLIA_CHEBO', 'YVAR_DE_GROOT', 'VETRANA']\n\n    Result of /check/ includes 1 track with label 'converted_mix'.\n    {\"label\":\"converted_mix\", \"type\":\"back\", \"url\":\"...\"}\n    "
      tags:
      - Voice Change
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoiceChangeParameters'
        required: true
      security:
      - ApiKeyHeaderAuth: []
  /api/v1/voice_packs/list/:
    post:
      operationId: voice_packs_list_packs
      summary: Lists voice packs available to the user
      parameters: []
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicePackListResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                anyOf:
                - $ref: '#/components/schemas/ApiV1ErrorResponse'
                - $ref: '#/components/schemas/CommonErrorResponse'
                title: Response
        '422':
          description: Unprocessable Entity
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CommonErrorResponse'
      description: Helps to find pack_id for /change_voice/ endpoint.
      tags:
      - Voice Change
      security:
      - ApiKeyHeaderAuth: []
components:
  schemas:
    ApiV1ErrorResponse:
      properties:
        detail:
          description: Error message.
          example: Idempotency key has already been used.
          title: Detail
          type: string
        code:
          description: Error code.
          example: idempotency_key_used
          title: Code
          type: string
      required:
      - detail
      - code
      title: ApiV1ErrorResponse
      type: object
    VoicePackListResponse:
      properties:
        packs:
          description: List of voice packs available to the user.
          items:
            $ref: '#/components/schemas/VoicePackInfo'
          title: Packs
          type: array
      required:
      - packs
      title: VoicePackListResponse
      type: object
    EncoderFormat:
      enum:
      - mp3
      - wav
      - flac
      - aac
      - ogg
      title: EncoderFormat
      type: string
    VoicePackInfo:
      properties:
        name:
          description: Name of the voice pack.
          example: Professional Narrator Voice Pack
          title: Name
          type: string
        pack_id:
          description: ID of the voice pack.
          example: f5dc9452-9374-4418-9288-02825bbd0016
          title: Pack Id
          type: string
        created:
          description: Creation timestamp of the voice pack.
          example: 1672531199
          title: Created
          type: integer
      required:
      - name
      - pack_id
      - created
      title: VoicePackInfo
      type: object
    VoiceChangeParameters:
      properties:
        source_id:
          description: ID of the source file to be processed.
          example: 2fe8f214-1771-4900-9e7e-570f823bd359
          format: uuid4
          title: Source Id
          type: string
        presets:
          $ref: '#/components/schemas/VoiceChangePresetsV1'
          description: Presets for converting the source file.
        idempotency_key:
          anyOf:
          - format: uuid4
            type: string
          - type: 'null'
          default: null
          description: '

            Unique uuid4 key to ensure idempotent requests.


            Prevents duplicate task execution with the same parameters.


            Can be reused until the task starts. Once processing begins, reusing this key will return an error.

            '
          title: Idempotency Key
      required:
      - source_id
      - presets
      title: VoiceChangeParameters
      type: object
    TonalityReference:
      enum:
      - source_file
      - voice_pack
      title: TonalityReference
      type: string
    CommonErrorResponse:
      properties:
        detail:
          anyOf:
          - type: string
          - additionalProperties: true
            type: object
          - items:
              additionalProperties: true
              type: object
            type: array
          description: Error details
          example:
            detail:
            - loc:
              - body
              - split_input
              - source_id
              msg: Field required
              type: missing
            - loc:
              - body
              - split_input
              - presets
              msg: Field required
              type: missing
          title: Detail
      required:
      - detail
      title: CommonErrorResponse
      type: object
    VoiceChangePresetsV1:
      properties:
        voice_pack_id:
          description: '

            ID of the voice pack to be used for voice conversion.


            Could be one of the legal packs, provided by us.


            Could be a custom voice pack from voice cloner, trained by the user(see /voice_packs/list/).


            '
          examples:
          - <user_private_pack_uuid4>
          - ALEX_KAYE
          - STASIA_FAYE
          - NICOLAAS_HAAS
          - NIK_ZEL
          - OLIA_CHEBO
          - YVAR_DE_GROOT
          - VETRANA
          title: Voice Pack Id
          type: string
        accent:
          default: 1.0
          description: '

            Float value, changing intensity in range from 0.0 to 1.0


            0.0 preserves the source file accent and 1.0 applies the voice pack accent.

            '
          example: 0.33
          maximum: 1.0
          minimum: 0.0
          title: Accent
          type: number
        tonality_reference:
          allOf:
          - $ref: '#/components/schemas/TonalityReference'
          default: source_file
          description: Tonality reference for voice conversion.
        dereverb_enabled:
          default: false
          description: '

            Enabling dereverb removes echo from the audio for clarity, which may slightly alter the voice.


            Disabling dereverb preserves the natural echo of the recording for authenticity.

            '
          title: Dereverb Enabled
          type: boolean
        encoder_format:
          anyOf:
          - $ref: '#/components/schemas/EncoderFormat'
          - type: 'null'
          default: null
          description: Format for output audio. If None - convert to source file format.
      required:
      - voice_pack_id
      title: VoiceChangePresetsV1
      type: object
    TaskResponse:
      properties:
        task_id:
          description: ID of the created task.
          example: e1fc1d8f-502e-4de0-bf3b-b30543d11c77
          title: Task Id
          type: string
      required:
      - task_id
      title: TaskResponse
      type: object
  securitySchemes:
    ApiKeyHeaderAuth:
      type: apiKey
      in: header
      name: X-License-Key