Amazon Polly API

openapi: 3.1.0
info:
  title: Amazon Polly API
  description: >-
    The Amazon Polly API enables you to synthesize speech from text using
    a variety of lifelike voices across multiple languages. You can also
    manage pronunciation lexicons and start long-running speech synthesis
    tasks.
  version: '2016-06-10'
  contact:
    name: AWS Support
    url: https://aws.amazon.com/premiumsupport/
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0.html
  x-logo:
    url: https://a0.awsstatic.com/libra-css/images/logos/aws_logo_smile_1200x630.png
servers:
- url: https://polly.{region}.amazonaws.com
  description: Amazon Polly regional endpoint
  variables:
    region:
      default: us-east-1
      description: AWS region
      enum:
      - us-east-1
      - us-east-2
      - us-west-1
      - us-west-2
      - eu-west-1
      - eu-west-2
      - eu-west-3
      - eu-central-1
      - ap-northeast-1
      - ap-northeast-2
      - ap-southeast-1
      - ap-southeast-2
      - ap-south-1
      - sa-east-1
      - ca-central-1
security:
- sigv4: []
tags:
- name: Lexicons
  description: Operations for managing pronunciation lexicons
- name: Speech Synthesis
  description: Operations for synthesizing speech from text
- name: Voices
  description: Operations for listing available voices
paths:
  /v1/speech:
    post:
      operationId: SynthesizeSpeech
      summary: Amazon Polly Synthesize Speech
      description: Synthesizes UTF-8 input text into an audio stream.
      tags:
      - Speech Synthesis
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SynthesizeSpeechInput'
      responses:
        '200':
          description: Speech audio stream
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
            audio/ogg:
              schema:
                type: string
                format: binary
            audio/pcm:
              schema:
                type: string
                format: binary
  /v1/voices:
    get:
      operationId: DescribeVoices
      summary: Amazon Polly List Available Voices
      description: Returns the list of voices that are available for use when synthesizing speech.
      tags:
      - Voices
      parameters:
      - name: Engine
        in: query
        schema:
          type: string
          enum:
          - standard
          - neural
          - long-form
          - generative
      - name: LanguageCode
        in: query
        schema:
          type: string
      responses:
        '200':
          description: Voices listed successfully
          content:
            application/json:
              schema:
                type: object
                properties:
                  Voices:
                    type: array
                    items:
                      $ref: '#/components/schemas/Voice'
  /v1/lexicons/{LexiconName}:
    put:
      operationId: PutLexicon
      summary: Amazon Polly Store a Pronunciation Lexicon
      description: Stores a pronunciation lexicon in an AWS Region.
      tags:
      - Lexicons
      parameters:
      - name: LexiconName
        in: path
        required: true
        schema:
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                Content:
                  type: string
                  description: Content of the PLS lexicon as string data
      responses:
        '200':
          description: Lexicon stored successfully
    get:
      operationId: GetLexicon
      summary: Amazon Polly Get a Pronunciation Lexicon
      description: Returns the content of the specified pronunciation lexicon.
      tags:
      - Lexicons
      parameters:
      - name: LexiconName
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Lexicon retrieved successfully
    delete:
      operationId: DeleteLexicon
      summary: Amazon Polly Delete a Pronunciation Lexicon
      description: Deletes the specified pronunciation lexicon stored in an AWS Region.
      tags:
      - Lexicons
      parameters:
      - name: LexiconName
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Lexicon deleted successfully
  /v1/lexicons:
    get:
      operationId: ListLexicons
      summary: Amazon Polly List Pronunciation Lexicons
      description: Returns a list of pronunciation lexicons stored in an AWS Region.
      tags:
      - Lexicons
      responses:
        '200':
          description: Lexicons listed successfully
components:
  securitySchemes:
    sigv4:
      type: apiKey
      name: Authorization
      in: header
      description: AWS Signature Version 4
  schemas:
    SynthesizeSpeechInput:
      type: object
      required:
      - OutputFormat
      - Text
      - VoiceId
      properties:
        Engine:
          type: string
          enum:
          - standard
          - neural
          - long-form
          - generative
          description: The engine to use for speech synthesis
        LanguageCode:
          type: string
          description: Language code for the synthesis request
        LexiconNames:
          type: array
          items:
            type: string
          description: List of lexicon names to apply during synthesis
        OutputFormat:
          type: string
          enum:
          - json
          - mp3
          - ogg_vorbis
          - pcm
          description: The format in which the returned output will be encoded
        SampleRate:
          type: string
          description: The audio frequency in Hz
        SpeechMarkTypes:
          type: array
          items:
            type: string
            enum:
            - sentence
            - ssml
            - viseme
            - word
        Text:
          type: string
          description: Input text to synthesize
        TextType:
          type: string
          enum:
          - ssml
          - text
          description: Whether the input text is plain text or SSML
        VoiceId:
          type: string
          description: Voice ID to use for the synthesis
    Voice:
      type: object
      properties:
        Gender:
          type: string
          enum:
          - Female
          - Male
        Id:
          type: string
          description: Amazon Polly assigned voice ID
        LanguageCode:
          type: string
        LanguageName:
          type: string
        Name:
          type: string
          description: Name of the voice
        SupportedEngines:
          type: array
          items:
            type: string
            enum:
            - standard
            - neural
            - long-form
            - generative