ElevenLabs Sound Effects API

openapi: 3.1.0
info:
  title: ElevenLabs Sound Effects API
  description: >-
    The ElevenLabs Sound Effects API generates cinematic sound effects from
    text descriptions. Developers can describe the desired sound in natural
    language and receive high-quality audio output. The API supports audio
    tags for controlling delivery, emotion, emphasis, pauses, and specific
    sound effects, making it suitable for game development, film production,
    and multimedia content creation.
  version: '1.0'
  contact:
    name: ElevenLabs Support
    url: https://help.elevenlabs.io
  termsOfService: https://elevenlabs.io/terms-of-service
externalDocs:
  description: ElevenLabs Sound Effects API Documentation
  url: https://elevenlabs.io/docs/api-reference/text-to-sound-effects/convert
servers:
  - url: https://api.elevenlabs.io
    description: Production Server
tags:
  - name: Sound Effects
    description: >-
      Endpoints for generating sound effects from text descriptions using
      AI models.
security:
  - apiKeyAuth: []
paths:
  /v1/sound-generation:
    post:
      operationId: createSoundEffect
      summary: Create sound effect
      description: >-
        Generates a sound effect from a text description. The description
        should detail the desired sound in natural language. Returns the
        generated audio in the specified format.
      tags:
        - Sound Effects
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SoundEffectRequest'
      responses:
        '200':
          description: Sound effect generated successfully
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
        '400':
          description: Bad request - invalid parameters
        '401':
          description: Unauthorized - invalid or missing API key
        '422':
          description: Unprocessable entity - validation error
components:
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: xi-api-key
      description: >-
        ElevenLabs API key passed in the xi-api-key header for authentication.
  schemas:
    SoundEffectRequest:
      type: object
      required:
        - text
      properties:
        text:
          type: string
          description: >-
            A natural language description of the sound effect to generate.
            Be specific about the type of sound, its characteristics, and
            any environmental context.
          maxLength: 1000
        duration_seconds:
          type: number
          description: >-
            The desired duration of the generated sound effect in seconds.
            If not provided, the model determines an appropriate length.
          minimum: 0.5
          maximum: 22
        prompt_influence:
          type: number
          description: >-
            Controls how closely the generation follows the text prompt.
            Higher values produce output more faithful to the description,
            while lower values allow more creative interpretation.
          minimum: 0
          maximum: 1
          default: 0.3