openapi: 3.1.0
info:
  title: PlayAI Agents TTS API
  description: 'PlayAI (formerly PlayHT) is a generative voice platform. The REST API

    covers text-to-speech generation (PlayDialog, Dialog 1.0 Turbo, and

    Play 3.0 Mini models), voice catalog, voice agents, external functions,

    and PlayNote document-to-audio jobs.


    Authentication uses two headers: `AUTHORIZATION` carries the secret API

    key, and `X-USER-ID` carries the PlayAI user identifier.

    '
  version: 1.0.0
  contact:
    name: API Evangelist
    email: kin@apievangelist.com
  license:
    name: Proprietary
servers:
- url: https://api.play.ai
  description: PlayAI production API
security:
- apiKey: []
  userId: []
tags:
- name: TTS
  description: Text-to-speech generation, streaming, and async jobs.
paths:
  /api/v1/tts:
    post:
      tags:
      - TTS
      summary: Create an async TTS job
      description: 'Convert text to speech with PlayAI models. Returns an async job that

        can be polled via GET /api/v1/tts/{asyncTtsJobId}.

        '
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TTSRequest'
      responses:
        '202':
          description: Async TTS job created.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TTSJob'
  /api/v1/tts/{asyncTtsJobId}:
    parameters:
    - $ref: '#/components/parameters/AsyncTtsJobId'
    get:
      tags:
      - TTS
      summary: Retrieve async TTS job status
      responses:
        '200':
          description: TTS job.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TTSJob'
  /api/v1/tts/stream:
    post:
      tags:
      - TTS
      summary: Stream speech in real time
      description: Streams audio bytes for the supplied text in real time.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TTSStreamRequest'
      responses:
        '200':
          description: Streamed audio bytes.
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
            audio/wav:
              schema:
                type: string
                format: binary
components:
  schemas:
    TTSRequest:
      type: object
      required:
      - text
      - voice
      properties:
        text:
          type: string
        voice:
          type: string
        model:
          type: string
          enum:
          - PlayDialog
          - Dialog-1.0-Turbo
          - Play3.0-mini
        outputFormat:
          type: string
          enum:
          - mp3
          - wav
          - ogg
          - flac
          - mulaw
        speed:
          type: number
    TTSJob:
      type: object
      properties:
        id:
          type: string
        status:
          type: string
          enum:
          - queued
          - processing
          - complete
          - failed
        outputUrl:
          type: string
          format: uri
        durationSeconds:
          type: number
        createdAt:
          type: string
          format: date-time
    TTSStreamRequest:
      allOf:
      - $ref: '#/components/schemas/TTSRequest'
  parameters:
    AsyncTtsJobId:
      name: asyncTtsJobId
      in: path
      required: true
      schema:
        type: string
  securitySchemes:
    apiKey:
      type: apiKey
      in: header
      name: AUTHORIZATION
      description: Secret API key issued in the PlayAI console.
    userId:
      type: apiKey
      in: header
      name: X-USER-ID
      description: PlayAI user identifier paired with the API key.