Amazon Polly Speech Synthesis API

Operations for synthesizing speech from text

OpenAPI Specification

amazon-polly-speech-synthesis-api-openapi.yml Raw ↑
openapi: 3.0.0
info:
  version: 2016-06-10
  x-release: v4
  title: Amazon Polly Lexicons Speech Synthesis API
  description: <p>Amazon Polly is a web service that makes it easy to synthesize speech from text.</p> <p>The Amazon Polly service provides API operations for synthesizing high-quality speech from plain text and Speech Synthesis Markup Language (SSML), along with managing pronunciations lexicons that enable you to get the best results for your application domain.</p>
  x-logo:
    url: https://api.apis.guru/v2/cache/logo/https_twitter.com_awscloud_profile_image.png
    backgroundColor: '#FFFFFF'
  termsOfService: https://aws.amazon.com/service-terms/
  contact:
    name: Mike Ralphson
    email: mike.ralphson@gmail.com
    url: https://github.com/mermade/aws2openapi
    x-twitter: PermittedSoc
  license:
    name: Apache 2.0 License
    url: http://www.apache.org/licenses/
  x-providerName: amazonaws.com
  x-serviceName: polly
  x-origin:
  - contentType: application/json
    url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/polly-2016-06-10.normal.json
    converter:
      url: https://github.com/mermade/aws2openapi
      version: 1.0.0
    x-apisguru-driver: external
  x-apiClientRegistration:
    url: https://portal.aws.amazon.com/gp/aws/developer/registration/index.html?nc2=h_ct
  x-apisguru-categories:
  - cloud
  x-preferred: true
servers:
- url: http://polly.{region}.amazonaws.com
  variables:
    region:
      description: The AWS region
      enum:
      - us-east-1
      - us-east-2
      - us-west-1
      - us-west-2
      - us-gov-west-1
      - us-gov-east-1
      - ca-central-1
      - eu-north-1
      - eu-west-1
      - eu-west-2
      - eu-west-3
      - eu-central-1
      - eu-south-1
      - af-south-1
      - ap-northeast-1
      - ap-northeast-2
      - ap-northeast-3
      - ap-southeast-1
      - ap-southeast-2
      - ap-east-1
      - ap-south-1
      - sa-east-1
      - me-south-1
      default: us-east-1
  description: The Amazon Polly multi-region endpoint
- url: https://polly.{region}.amazonaws.com
  variables:
    region:
      description: The AWS region
      enum:
      - us-east-1
      - us-east-2
      - us-west-1
      - us-west-2
      - us-gov-west-1
      - us-gov-east-1
      - ca-central-1
      - eu-north-1
      - eu-west-1
      - eu-west-2
      - eu-west-3
      - eu-central-1
      - eu-south-1
      - af-south-1
      - ap-northeast-1
      - ap-northeast-2
      - ap-northeast-3
      - ap-southeast-1
      - ap-southeast-2
      - ap-east-1
      - ap-south-1
      - sa-east-1
      - me-south-1
      default: us-east-1
  description: The Amazon Polly multi-region endpoint
- url: http://polly.{region}.amazonaws.com.cn
  variables:
    region:
      description: The AWS region
      enum:
      - cn-north-1
      - cn-northwest-1
      default: cn-north-1
  description: The Amazon Polly endpoint for China (Beijing) and China (Ningxia)
- url: https://polly.{region}.amazonaws.com.cn
  variables:
    region:
      description: The AWS region
      enum:
      - cn-north-1
      - cn-northwest-1
      default: cn-north-1
  description: The Amazon Polly endpoint for China (Beijing) and China (Ningxia)
security:
- hmac: []
tags:
- name: Speech Synthesis
  description: Operations for synthesizing speech from text
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
components:
  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
  securitySchemes:
    hmac:
      type: apiKey
      name: Authorization
      in: header
      description: Amazon Signature authorization v4
      x-amazon-apigateway-authtype: awsSigv4
externalDocs:
  description: Amazon Web Services documentation
  url: https://docs.aws.amazon.com/polly/