openapi: 3.1.0
info:
  title: OpenAI APIs OpenAI Assistants Speech API
  description: API for building AI assistants with custom instructions, knowledge retrieval, code execution, and function calling capabilities. Supports managing assistants, threads, messages, and runs.
  version: '2.0'
  contact:
    name: OpenAI Support
    email: support@openai.com
    url: https://help.openai.com
  termsOfService: https://openai.com/policies/terms-of-use
servers:
- url: https://api.openai.com/v1
  description: OpenAI Production API
security:
- bearerAuth: []
tags:
- name: Speech
  description: Text-to-speech operations
paths:
  /audio/speech:
    post:
      operationId: createSpeech
      summary: OpenAI APIs Create speech
      description: Generates audio from the input text using the specified voice and model.
      tags:
      - Speech
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateSpeechRequest'
      responses:
        '200':
          description: Audio file containing the generated speech
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
            audio/opus:
              schema:
                type: string
                format: binary
            audio/aac:
              schema:
                type: string
                format: binary
            audio/flac:
              schema:
                type: string
                format: binary
            audio/wav:
              schema:
                type: string
                format: binary
            audio/pcm:
              schema:
                type: string
                format: binary
        '400':
          description: Invalid request
        '401':
          description: Unauthorized - invalid or missing API key
        '429':
          description: Rate limit exceeded
components:
  schemas:
    CreateSpeechRequest:
      type: object
      required:
      - model
      - input
      - voice
      properties:
        model:
          type: string
          description: The TTS model to use (tts-1 or tts-1-hd)
          examples:
          - tts-1
        input:
          type: string
          maxLength: 4096
          description: The text to generate audio for
        voice:
          type: string
          enum:
          - alloy
          - echo
          - fable
          - onyx
          - nova
          - shimmer
          description: The voice to use when generating the audio
        response_format:
          type: string
          enum:
          - mp3
          - opus
          - aac
          - flac
          - wav
          - pcm
          default: mp3
          description: The format of the audio output
        speed:
          type: number
          minimum: 0.25
          maximum: 4.0
          default: 1.0
          description: The speed of the generated audio
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: OpenAI API key passed as a Bearer token
externalDocs:
  description: OpenAI Assistants API Documentation
  url: https://platform.openai.com/docs/api-reference/assistants