openapi: 3.0.3
info:
  title: Uberduck Text To Speech Conversational Text-to-Speech API
  description: The Uberduck API converts text to natural-sounding speech across a catalog of voices and provider-backed models (AWS Polly, Google Cloud, Azure), lists and filters those voices, creates instant zero-shot voice clones from reference audio, and mints short-lived LiveKit tokens for real-time conversational AI voice calls. All requests are HTTPS request/response and authenticate with a Bearer API key generated in the Uberduck account settings. API access is a paid feature available on the Creator plan and above. This document is transcribed from Uberduck's published OpenAPI (https://api.uberduck.ai/openapi.json, version 0.1.0) and its Swagger UI at https://api.uberduck.ai/docs.
  version: 0.1.0
  contact:
    name: Uberduck
    url: https://uberduck.ai
servers:
- url: https://api.uberduck.ai
  description: Uberduck production API
security:
- HTTPBearer: []
tags:
- name: Text-to-Speech
  description: Synthesize speech from text using a chosen voice and model.
paths:
  /v1/text-to-speech:
    post:
      operationId: textToSpeech
      tags:
      - Text-to-Speech
      summary: Text To Speech
      description: Convert up to 10,000 characters of text into speech using a specified voice and model. Returns a URL to the generated audio.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TextToSpeechRequest'
      responses:
        '200':
          description: Generated audio.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TextToSpeechResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
        '422':
          $ref: '#/components/responses/ValidationError'
components:
  responses:
    NotFound:
      description: Resource not found.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    ValidationError:
      description: Validation error.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/HTTPValidationError'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    BadRequest:
      description: Bad request.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  schemas:
    TextToSpeechResponse:
      type: object
      description: Response schema for the text-to-speech endpoint.
      required:
      - audio_url
      properties:
        audio_url:
          type: string
          description: URL to the generated audio.
    ValidationError:
      type: object
      required:
      - loc
      - msg
      - type
      properties:
        loc:
          type: array
          items:
            anyOf:
            - type: string
            - type: integer
        msg:
          type: string
        type:
          type: string
    TextToSpeechRequest:
      type: object
      description: Request schema for the text-to-speech endpoint.
      required:
      - text
      - voice
      properties:
        text:
          type: string
          minLength: 1
          maxLength: 10000
          description: The text to convert to speech.
        voice:
          type: string
          description: The voice ID to use.
        model:
          type: string
          description: The model to use for speech generation.
        extended:
          type: object
          description: Common parameters supported by many models.
        model_specific:
          type: object
          description: Parameters specific to the chosen model.
        output_format:
          type: string
          default: mp3
          description: Desired output format (mp3, wav, etc.).
    ErrorResponse:
      type: object
      description: API error response format.
      required:
      - error
      properties:
        error:
          $ref: '#/components/schemas/ErrorDetail'
    ErrorDetail:
      type: object
      description: Details for an API error.
      required:
      - code
      - message
      properties:
        code:
          type: string
        message:
          type: string
        details:
          type: object
    HTTPValidationError:
      type: object
      properties:
        detail:
          type: array
          items:
            $ref: '#/components/schemas/ValidationError'
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer
      description: Bearer API key generated in Uberduck account settings under the API section.