BudgetPixel Music API

openapi: 3.2.0
info:
  title: Budgetpixel Music API
  version: '2026-06-20'
  contact:
    email: support@budgetpixel.com
    name: BudgetPixel Support
  description: 'Operations tagged Music across 2 of this provider''s published API definitions: budgetpixel-openapi.yaml, budgetpixel-openapi.yaml. Each path carries the servers of the definition it was published in.'
servers:
- description: Production
  url: https://api.budgetpixel.com/v1
security:
- ApiKeyAuth: []
tags:
- description: Music generation models
  name: Music
paths:
  /audios/lyria-3:
    post:
      description: 'Google Lyria 3 — high-fidelity music from a text prompt, with optional lyrics and up to 10 reference images to condition the mood. MP3 output (SynthID-watermarked).


        **Asynchronous.** Returns a job `id` (the track is not in this response). Poll [`GET /v1/audios/{id}`](/api-reference/audios/get-music-job-status) until `status` is `succeeded` — the track URL is in that response''s `audio_url`.'
      operationId: createAudio_lyria_3
      requestBody:
        content:
          application/json:
            schema:
              properties:
                images:
                  description: Optional reference images (up to 10) to condition the track's mood/theme. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads.
                  items:
                    type: string
                  maxItems: 10
                  type: array
                lyrics:
                  description: Optional lyrics (up to 3000 characters).
                  type: string
                prompt:
                  description: Description of the music to generate (10-2000 characters).
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateAudioResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate music with Lyria 3
      tags:
      - Music
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /audios/mureka-v9:
    post:
      description: 'Mureka V9 — songs that sing your exact lyrics (structural tags like [verse]/[chorus] supported) with a vocal gender preference, or instrumental/BGM tracks from a prompt. MP3 output.


        **Asynchronous.** Returns a job `id` (the track is not in this response). Poll [`GET /v1/audios/{id}`](/api-reference/audios/get-music-job-status) until `status` is `succeeded` — the track URL is in that response''s `audio_url`.'
      operationId: createAudio_mureka_v9
      requestBody:
        content:
          application/json:
            schema:
              properties:
                instrumental:
                  default: false
                  description: Generate an instrumental/BGM track from the prompt (no vocals, lyrics ignored).
                  type: boolean
                lyrics:
                  description: Lyrics to sing verbatim (1-5000 characters; [verse]/[chorus]/[bridge] tags supported). Required for songs; ignored for instrumental tracks.
                  type: string
                prompt:
                  description: Style hint (up to 1024 characters). Optional for songs; required for instrumental tracks.
                  type: string
                vocal_gender:
                  default: auto
                  description: Preferred vocal gender for songs.
                  enum:
                  - auto
                  - female
                  - male
                  type: string
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateAudioResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate music with Mureka V9
      tags:
      - Music
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /audios/music-2.6:
    post:
      description: 'MiniMax Music 2.6 — full-length songs from a style prompt and/or your own lyrics. Lyrics optimizer can write or polish lyrics from the prompt; instrumental mode skips vocals. MP3 or WAV output.


        **Asynchronous.** Returns a job `id` (the track is not in this response). Poll [`GET /v1/audios/{id}`](/api-reference/audios/get-music-job-status) until `status` is `succeeded` — the track URL is in that response''s `audio_url`.'
      operationId: createAudio_music_2_6
      requestBody:
        content:
          application/json:
            schema:
              properties:
                format:
                  default: wav
                  description: Output audio format. Defaults to wav (lossless); choose mp3 for a smaller file.
                  enum:
                  - wav
                  - mp3
                  type: string
                instrumental:
                  default: false
                  description: Generate an instrumental track (no vocals).
                  type: boolean
                lyrics:
                  description: Lyrics to sing (1-3500 characters). Required unless instrumental is true or lyrics_optimizer is true (the optimizer writes lyrics from the prompt).
                  type: string
                lyrics_optimizer:
                  default: true
                  description: Let the model write or polish lyrics from the prompt. Default true.
                  type: boolean
                prompt:
                  description: Style/mood description of the track (up to 2000 characters). Optional when lyrics are provided.
                  type: string
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateAudioResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate music with Music 2.6
      tags:
      - Music
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /audios/music-3.0:
    post:
      description: 'MiniMax Music 3.0 — the latest MiniMax music model: full-length songs from a style prompt and/or your own lyrics. Lyrics optimizer can write or polish lyrics from the prompt; instrumental mode skips vocals. WAV or MP3 output.


        **Asynchronous.** Returns a job `id` (the track is not in this response). Poll [`GET /v1/audios/{id}`](/api-reference/audios/get-music-job-status) until `status` is `succeeded` — the track URL is in that response''s `audio_url`.'
      operationId: createAudio_music_3_0
      requestBody:
        content:
          application/json:
            schema:
              properties:
                format:
                  default: wav
                  description: Output audio format. Defaults to wav (lossless); choose mp3 for a smaller file.
                  enum:
                  - wav
                  - mp3
                  type: string
                instrumental:
                  default: false
                  description: Generate an instrumental track (no vocals).
                  type: boolean
                lyrics:
                  description: Lyrics to sing (1-3500 characters). Required unless instrumental is true or lyrics_optimizer is true (the optimizer writes lyrics from the prompt).
                  type: string
                lyrics_optimizer:
                  default: true
                  description: Let the model write or polish lyrics from the prompt. Default true.
                  type: boolean
                prompt:
                  description: Style/mood description of the track (up to 2000 characters). Optional when lyrics are provided.
                  type: string
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateAudioResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate music with Music 3.0
      tags:
      - Music
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
  /audios/sonilo-music:
    post:
      description: 'Sonilo text-to-music — licensed instrumental and background music of an exact length (5-360 seconds) from a text prompt: soundtracks for videos, ads, apps and games. Priced per second of the requested duration with a 10-second minimum (rate in GET /v1/models; POST /v1/cost quotes the exact price). MP3 or WAV output.


        **Asynchronous.** Returns a job `id` (the track is not in this response). Poll [`GET /v1/audios/{id}`](/api-reference/audios/get-music-job-status) until `status` is `succeeded` — the track URL is in that response''s `audio_url`. Charged per second of the requested `duration` (10-second minimum; rate in `GET /v1/models`) on success only; `POST /v1/cost` quotes the exact price.'
      operationId: createAudio_sonilo_music
      requestBody:
        content:
          application/json:
            schema:
              properties:
                duration:
                  default: 30
                  description: Length of the track in seconds (5-360). Billed per second with a 10-second minimum.
                  maximum: 360
                  minimum: 5
                  type: integer
                format:
                  default: mp3
                  description: Output audio format.
                  enum:
                  - mp3
                  - wav
                  type: string
                prompt:
                  description: Description of the music (up to 2000 characters; even a few words work), e.g. "30 seconds of upbeat electronic instrumental for a product launch video, no vocals".
                  type: string
              required:
              - prompt
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateAudioResponse'
          description: Job accepted.
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '429':
          $ref: '#/components/responses/TooManyRequests'
      summary: Generate music with Sonilo Music
      tags:
      - Music
    servers:
    - description: Production
      url: https://api.budgetpixel.com/v1
components:
  responses:
    Forbidden:
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
      description: Authenticated but not permitted (plan gate, ownership, account restriction). Content-moderation blocks are 400, not 403.
    BadRequest:
      content:
        application/json:
          schema:
            oneOf:
            - $ref: '#/components/schemas/Error'
            - $ref: '#/components/schemas/ModerationBlocked'
      description: The request was malformed, referenced an unavailable model, or was blocked by input content moderation (moderation blocks carry a `restriction_reason` — see ModerationBlocked).
    TooManyRequests:
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
      description: Rate or queue limit reached. Retry after a short delay.
    Unauthorized:
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
      description: Missing or invalid API key.
  schemas:
    ModerationBlocked:
      description: Returned (with HTTP 400) when the input content moderation gate blocks a generation request. The block is a property of the request's prompt or input media — reword the prompt or change the input and retry. Branch on `restriction_reason`, which is stable and machine-readable.
      properties:
        error:
          description: Human-readable explanation of the block.
          type: string
        restriction_reason:
          description: Stable machine-readable block reason.
          enum:
          - input_csam
          - input_explicit_adult
          - input_upload_nudity
          - input_celebrity_likeness
          - strict_model_nsfw
          type: string
      required:
      - error
      - restriction_reason
      type: object
    CreateAudioResponse:
      properties:
        id:
          description: Opaque job id — use it to poll status.
          example: aud_a1b2c3d4e5f6
          type: string
        message:
          type: string
        model:
          type: string
        status:
          $ref: '#/components/schemas/JobStatus'
      type: object
    JobStatus:
      description: Lifecycle state. `succeeded`/`failed`/`timeout` are terminal.
      enum:
      - pending
      - starting
      - processing
      - completing
      - succeeded
      - failed
      - timeout
      type: string
    Error:
      properties:
        error:
          properties:
            code:
              description: Stable machine-readable code.
              example: model_not_available
              type: string
            message:
              type: string
            type:
              description: Error category.
              example: invalid_request_error
              type: string
          required:
          - type
          - code
          - message
          type: object
      required:
      - error
      type: object
  securitySchemes:
    ApiKeyAuth:
      bearerFormat: bpx_live_*
      description: 'API key as a bearer token: Authorization: Bearer bpx_live_xxx'
      scheme: bearer
      type: http
x-refined-from:
- budgetpixel-openapi.yaml
- budgetpixel-openapi.yaml