openapi: 3.0.1
info:
  title: Speechify Voice Audio Voices API
  description: Specification of the Speechify Voice API (Text-to-Speech). The API synthesizes lifelike speech from plain text or SSML in 30+ languages, supports non-streaming and streaming audio, lists available voices, and creates and deletes instant voice clones. All requests authenticate with a Bearer API key.
  termsOfService: https://speechify.com/terms/
  contact:
    name: Speechify Support
    url: https://docs.sws.speechify.com
  version: '1.0'
servers:
- url: https://api.sws.speechify.com
security:
- bearerAuth: []
tags:
- name: Voices
paths:
  /v1/voices:
    get:
      operationId: listVoices
      tags:
      - Voices
      summary: List voices
      description: Returns the available voices, including pre-set Speechify voices and any personal cloned voices on the account.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Voice'
        '401':
          description: Unauthorized - missing or invalid API key.
    post:
      operationId: createVoice
      tags:
      - Voices
      summary: Create a voice clone
      description: Creates an instant personal voice clone from a 10-30 second audio sample. Requires explicit consent identifying the person who owns the voice. Submitted as multipart/form-data.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/CreateVoiceRequest'
      responses:
        '200':
          description: The created personal voice.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Voice'
        '401':
          description: Unauthorized - missing or invalid API key.
        '422':
          description: Unprocessable entity - invalid sample or missing consent.
  /v1/voices/{id}:
    delete:
      operationId: deleteVoice
      tags:
      - Voices
      summary: Delete a voice
      description: Deletes a personal (cloned) voice by its id.
      parameters:
      - name: id
        in: path
        required: true
        description: The id of the personal voice to delete.
        schema:
          type: string
      responses:
        '204':
          description: The voice was deleted.
        '401':
          description: Unauthorized - missing or invalid API key.
        '404':
          description: The voice was not found.
components:
  schemas:
    CreateVoiceRequest:
      type: object
      required:
      - name
      - sample
      - consent
      properties:
        name:
          type: string
          description: Display name for the cloned voice.
        sample:
          type: string
          format: binary
          description: A 10-30 second audio sample of the voice to clone.
        consent:
          type: string
          description: JSON string containing the fullName and email of the person who owns the voice, confirming the voice belongs to you or someone you represent.
          example: '{"fullName":"Jane Doe","email":"jane@example.com"}'
        gender:
          type: string
          enum:
          - male
          - female
          - notSpecified
        locale:
          type: string
          description: Primary locale of the voice, e.g. en-US.
    Voice:
      type: object
      properties:
        id:
          type: string
          description: The voice id used as voice_id when synthesizing speech.
        display_name:
          type: string
          description: Human-readable name of the voice.
        type:
          type: string
          description: Whether the voice is a pre-set Speechify voice or a personal clone.
          enum:
          - shared
          - personal
        gender:
          type: string
          enum:
          - male
          - female
          - notSpecified
        locale:
          type: string
          description: Primary locale of the voice, e.g. en-US.
        tags:
          type: array
          items:
            type: string
        models:
          type: array
          description: Models the voice supports.
          items:
            type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Pass your Speechify API key as a Bearer token in the Authorization header, e.g. "Authorization: Bearer $SPEECHIFY_API_KEY".'