Amazon Polly Synthesis Tasks API

openapi: 3.1.0
info:
  title: Amazon Polly Synthesis Tasks API
  version: '2016-06-10'
  description: Generated from AWS's published Smithy model for Amazon Polly. 3 operation(s).
  contact:
    name: Amazon Web Services
    url: https://aws.amazon.com/contact-us/
  license:
    name: Apache 2.0
    identifier: Apache-2.0
    url: https://github.com/aws/api-models-aws/blob/main/LICENSE
servers:
- url: https://polly.{region}.amazonaws.com
  variables:
    region:
      default: us-east-1
security:
- sigv4: []
paths:
  /v1/synthesisTasks/{TaskId}:
    get:
      operationId: GetSpeechSynthesisTask
      summary: Get Speech Synthesis Task
      description: Retrieves a specific SpeechSynthesisTask object based on its TaskID. This object contains information about
        the given speech synthesis task, including the status of the task, and a link to the S3 bucket containing the output
        of the task.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetSpeechSynthesisTaskOutput'
        '400':
          description: InvalidTaskIdException; SynthesisTaskNotFoundException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InvalidTaskIdException'
        '500':
          description: ServiceFailureException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceFailureException'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GetSpeechSynthesisTaskInput'
      tags:
      - Synthesis Tasks
  /v1/synthesisTasks:
    get:
      operationId: ListSpeechSynthesisTasks
      summary: List Speech Synthesis Tasks
      description: Returns a list of SpeechSynthesisTask objects ordered by their creation date. This operation can filter
        the tasks by their status, for example, allowing users to list only tasks that are completed.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListSpeechSynthesisTasksOutput'
        '400':
          description: InvalidNextTokenException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InvalidNextTokenException'
        '500':
          description: ServiceFailureException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceFailureException'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ListSpeechSynthesisTasksInput'
      tags:
      - Synthesis Tasks
    post:
      operationId: StartSpeechSynthesisTask
      summary: Start Speech Synthesis Task
      description: Allows the creation of an asynchronous synthesis task, by starting a new SpeechSynthesisTask. This operation
        requires all the standard information needed for speech synthesis, plus the name of an Amazon S3 bucket for the service
        to store the output of the synthesis task and two optional parameters (OutputS3KeyPrefix and SnsTopicArn). Once the
        synthesis task is created, this operation will return a SpeechSynthesisTask object, which will include an identifier
        of this task as well as the current status. The SpeechSynthesisTask object is available for 72 hours after starting
        the asynchronous synthesis task.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StartSpeechSynthesisTaskOutput'
        '400':
          description: EngineNotSupportedException; InvalidS3BucketException; InvalidS3KeyException; InvalidSampleRateException;
            InvalidSnsTopicArnException; InvalidSsmlException; LanguageNotSupportedException; MarksNotSupportedForFormatException;
            SsmlMarksNotSupportedForTextTypeException; TextLengthExceededException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EngineNotSupportedException'
        '404':
          description: LexiconNotFoundException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/LexiconNotFoundException'
        '500':
          description: ServiceFailureException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceFailureException'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/StartSpeechSynthesisTaskInput'
      tags:
      - Synthesis Tasks
components:
  securitySchemes:
    sigv4:
      type: apiKey
      in: header
      name: Authorization
      description: AWS Signature Version 4. The Authorization header carries an AWS4-HMAC-SHA256 signature over the canonical
        request, with X-Amz-Date (and X-Amz-Security-Token for temporary credentials). Not a bearer token.
      x-aws-sigv4:
        signingName: polly
  schemas:
    EngineNotSupportedException:
      type: object
      properties:
        message:
          type: string
    GetSpeechSynthesisTaskInput:
      type: object
      properties:
        TaskId:
          type: string
          description: The Amazon Polly generated identifier for a speech synthesis task.
      required:
      - TaskId
    GetSpeechSynthesisTaskOutput:
      type: object
      properties:
        SynthesisTask:
          $ref: '#/components/schemas/SynthesisTask'
    InvalidNextTokenException:
      type: object
      properties:
        message:
          type: string
    InvalidTaskIdException:
      type: object
      properties:
        message:
          type: string
    LexiconNotFoundException:
      type: object
      properties:
        message:
          type: string
    ListSpeechSynthesisTasksInput:
      type: object
      properties:
        MaxResults:
          type: integer
          description: Maximum number of speech synthesis tasks returned in a List operation.
        NextToken:
          type: string
          description: The pagination token to use in the next request to continue the listing of speech synthesis tasks.
        Status:
          type: string
          enum:
          - scheduled
          - inProgress
          - completed
          - failed
          description: Status of the speech synthesis tasks returned in a List operation
    ListSpeechSynthesisTasksOutput:
      type: object
      properties:
        NextToken:
          type: string
          description: An opaque pagination token returned from the previous List operation in this request. If present, this
            indicates where to continue the listing.
        SynthesisTasks:
          type: array
          items:
            $ref: '#/components/schemas/SynthesisTask'
          description: List of SynthesisTask objects that provides information from the specified task in the list request,
            including output format, creation time, task status, and so on.
    ServiceFailureException:
      type: object
      properties:
        message:
          type: string
    StartSpeechSynthesisTaskInput:
      type: object
      properties:
        Engine:
          type: string
          enum:
          - standard
          - neural
          - long-form
          - generative
          description: Specifies the engine (standard, neural, long-form or generative) for Amazon Polly to use when processing
            input text for speech synthesis. Using a voice that is not supported for the engine selected will result in an
            error.
        LanguageCode:
          type: string
          enum:
          - arb
          - cmn-CN
          - cy-GB
          - da-DK
          - de-DE
          - en-AU
          - en-GB
          - en-GB-WLS
          - en-IN
          - en-US
          - es-ES
          - es-MX
          - es-US
          - fr-CA
          - fr-FR
          - is-IS
          - it-IT
          - ja-JP
          - hi-IN
          - ko-KR
          - nb-NO
          - nl-NL
          - pl-PL
          - pt-BR
          - pt-PT
          - ro-RO
          - ru-RU
          - sv-SE
          - tr-TR
          - en-NZ
          - en-ZA
          - ca-ES
          - de-AT
          - yue-CN
          - ar-AE
          - fi-FI
          - en-IE
          - nl-BE
          - fr-BE
          - cs-CZ
          - de-CH
          - en-SG
          description: Optional language code for the Speech Synthesis request. This is only necessary if using a bilingual
            voice, such as Aditi, which can be used for either Indian English (en-IN) or Hindi (hi-IN). If a bilingual voice
            is used and no language code is specified, Amazon Polly uses the default language of the bilingual voice. The
            default language for any voice is the one returned by the DescribeVoices operation for the LanguageCode parameter.
            For example, if no language code is specified, Aditi will use Indian English rather than Hindi.
        LexiconNames:
          type: array
          items:
            type: string
          description: List of one or more pronunciation lexicon names you want the service to apply during synthesis. Lexicons
            are applied only if the language of the lexicon is the same as the language of the voice.
        OutputFormat:
          type: string
          enum:
          - json
          - mp3
          - ogg_opus
          - ogg_vorbis
          - pcm
          - mulaw
          - alaw
          description: The format in which the returned output will be encoded. For audio stream, this will be mp3, ogg_vorbis,
            ogg_opus, mu-law, a-law, or pcm. For speech marks, this will be json.
        OutputS3BucketName:
          type: string
          description: Amazon S3 bucket name to which the output file will be saved.
        OutputS3KeyPrefix:
          type: string
          description: The Amazon S3 key prefix for the output speech file.
        SampleRate:
          type: string
          description: The audio frequency specified in Hz. The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050",
            and "24000". The default value for standard voices is "22050". The default value for neural voices is "24000".
            The default value for long-form voices is "24000". The default value for generative voices is "24000". Valid values
            for pcm are "8000" and "16000" The default value is "16000". Valid value for ogg_opus is "48000". Valid value
            for mu-law and a-law is "8000".
        SnsTopicArn:
          type: string
          description: ARN for the SNS topic optionally used for providing status notification for a speech synthesis task.
        SpeechMarkTypes:
          type: array
          items:
            type: string
            enum:
            - sentence
            - ssml
            - viseme
            - word
          description: The type of speech marks returned for the input text.
        Text:
          type: string
          description: The input text to synthesize. If you specify ssml as the TextType, follow the SSML format for the input
            text.
        TextType:
          type: string
          enum:
          - ssml
          - text
          description: Specifies whether the input text is plain text or SSML. The default value is plain text.
        VoiceId:
          type: string
          enum:
          - Aditi
          - Amy
          - Astrid
          - Bianca
          - Brian
          - Camila
          - Carla
          - Carmen
          - Celine
          - Chantal
          - Conchita
          - Cristiano
          - Dora
          - Emma
          - Enrique
          - Ewa
          - Filiz
          - Gabrielle
          - Geraint
          - Giorgio
          - Gwyneth
          - Hans
          - Ines
          - Ivy
          - Jacek
          - Jan
          - Joanna
          - Joey
          - Justin
          - Karl
          - Kendra
          - Kevin
          - Kimberly
          - Lea
          - Liv
          - Lotte
          - Lucia
          - Lupe
          - Mads
          - Maja
          - Marlene
          - Mathieu
          - Matthew
          - Maxim
          - Mia
          - Miguel
          - Mizuki
          - Naja
          - Nicole
          - Olivia
          - Penelope
          - Raveena
          - Ricardo
          - Ruben
          - Russell
          - Salli
          - Seoyeon
          - Takumi
          - Tatyana
          - Vicki
          - Vitoria
          - Zeina
          - Zhiyu
          - Aria
          - Ayanda
          - Arlet
          - Hannah
          - Arthur
          - Daniel
          - Liam
          - Pedro
          - Kajal
          - Hiujin
          - Laura
          - Elin
          - Ida
          - Suvi
          - Ola
          - Hala
          - Andres
          - Sergio
          - Remi
          - Adriano
          - Thiago
          - Ruth
          - Stephen
          - Kazuha
          - Tomoko
          - Niamh
          - Sofie
          - Lisa
          - Isabelle
          - Zayd
          - Danielle
          - Gregory
          - Burcu
          - Jitka
          - Sabrina
          - Jasmine
          - Jihye
          - Ambre
          - Beatrice
          - Florian
          - Lennart
          - Lorenzo
          - Tiffany
          - Arjun
          - Carlos
          - Carolina
          - Curtis
          - Hyunduk
          - Kenneth
          - Kiara
          - Leo
          - Nate
          - Tina
          description: Voice ID to use for the synthesis.
      required:
      - OutputFormat
      - OutputS3BucketName
      - Text
      - VoiceId
    StartSpeechSynthesisTaskOutput:
      type: object
      properties:
        SynthesisTask:
          $ref: '#/components/schemas/SynthesisTask'
    SynthesisTask:
      type: object
      properties:
        Engine:
          type: string
          enum:
          - standard
          - neural
          - long-form
          - generative
          description: Specifies the engine (standard, neural, long-form or generative) for Amazon Polly to use when processing
            input text for speech synthesis. Using a voice that is not supported for the engine selected will result in an
            error.
        TaskId:
          type: string
          description: The Amazon Polly generated identifier for a speech synthesis task.
        TaskStatus:
          type: string
          enum:
          - scheduled
          - inProgress
          - completed
          - failed
          description: Current status of the individual speech synthesis task.
        TaskStatusReason:
          type: string
          description: Reason for the current status of a specific speech synthesis task, including errors if the task has
            failed.
        OutputUri:
          type: string
          description: Pathway for the output speech file.
        CreationTime:
          type: string
          format: date-time
          description: Timestamp for the time the synthesis task was started.
        RequestCharacters:
          type: integer
          description: Number of billable characters synthesized.
        SnsTopicArn:
          type: string
          description: ARN for the SNS topic optionally used for providing status notification for a speech synthesis task.
        LexiconNames:
          type: array
          items:
            type: string
          description: List of one or more pronunciation lexicon names you want the service to apply during synthesis. Lexicons
            are applied only if the language of the lexicon is the same as the language of the voice.
        OutputFormat:
          type: string
          enum:
          - json
          - mp3
          - ogg_opus
          - ogg_vorbis
          - pcm
          - mulaw
          - alaw
          description: The format in which the returned output will be encoded. For audio stream, this will be mp3, ogg_vorbis,
            ogg_opus, mu-law, a-law, or pcm. For speech marks, this will be json.
        SampleRate:
          type: string
          description: The audio frequency specified in Hz. The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050",
            and "24000". The default value for standard voices is "22050". The default value for neural voices is "24000".
            The default value for long-form voices is "24000". The default value for generative voices is "24000". Valid values
            for pcm are "8000" and "16000" The default value is "16000". Valid value for ogg_opus is "48000". Valid value
            for mu-law and a-law is "8000".
        SpeechMarkTypes:
          type: array
          items:
            type: string
            enum:
            - sentence
            - ssml
            - viseme
            - word
          description: The type of speech marks returned for the input text.
        TextType:
          type: string
          enum:
          - ssml
          - text
          description: Specifies whether the input text is plain text or SSML. The default value is plain text.
        VoiceId:
          type: string
          enum:
          - Aditi
          - Amy
          - Astrid
          - Bianca
          - Brian
          - Camila
          - Carla
          - Carmen
          - Celine
          - Chantal
          - Conchita
          - Cristiano
          - Dora
          - Emma
          - Enrique
          - Ewa
          - Filiz
          - Gabrielle
          - Geraint
          - Giorgio
          - Gwyneth
          - Hans
          - Ines
          - Ivy
          - Jacek
          - Jan
          - Joanna
          - Joey
          - Justin
          - Karl
          - Kendra
          - Kevin
          - Kimberly
          - Lea
          - Liv
          - Lotte
          - Lucia
          - Lupe
          - Mads
          - Maja
          - Marlene
          - Mathieu
          - Matthew
          - Maxim
          - Mia
          - Miguel
          - Mizuki
          - Naja
          - Nicole
          - Olivia
          - Penelope
          - Raveena
          - Ricardo
          - Ruben
          - Russell
          - Salli
          - Seoyeon
          - Takumi
          - Tatyana
          - Vicki
          - Vitoria
          - Zeina
          - Zhiyu
          - Aria
          - Ayanda
          - Arlet
          - Hannah
          - Arthur
          - Daniel
          - Liam
          - Pedro
          - Kajal
          - Hiujin
          - Laura
          - Elin
          - Ida
          - Suvi
          - Ola
          - Hala
          - Andres
          - Sergio
          - Remi
          - Adriano
          - Thiago
          - Ruth
          - Stephen
          - Kazuha
          - Tomoko
          - Niamh
          - Sofie
          - Lisa
          - Isabelle
          - Zayd
          - Danielle
          - Gregory
          - Burcu
          - Jitka
          - Sabrina
          - Jasmine
          - Jihye
          - Ambre
          - Beatrice
          - Florian
          - Lennart
          - Lorenzo
          - Tiffany
          - Arjun
          - Carlos
          - Carolina
          - Curtis
          - Hyunduk
          - Kenneth
          - Kiara
          - Leo
          - Nate
          - Tina
          description: Voice ID to use for the synthesis.
        LanguageCode:
          type: string
          enum:
          - arb
          - cmn-CN
          - cy-GB
          - da-DK
          - de-DE
          - en-AU
          - en-GB
          - en-GB-WLS
          - en-IN
          - en-US
          - es-ES
          - es-MX
          - es-US
          - fr-CA
          - fr-FR
          - is-IS
          - it-IT
          - ja-JP
          - hi-IN
          - ko-KR
          - nb-NO
          - nl-NL
          - pl-PL
          - pt-BR
          - pt-PT
          - ro-RO
          - ru-RU
          - sv-SE
          - tr-TR
          - en-NZ
          - en-ZA
          - ca-ES
          - de-AT
          - yue-CN
          - ar-AE
          - fi-FI
          - en-IE
          - nl-BE
          - fr-BE
          - cs-CZ
          - de-CH
          - en-SG
          description: Optional language code for a synthesis task. This is only necessary if using a bilingual voice, such
            as Aditi, which can be used for either Indian English (en-IN) or Hindi (hi-IN). If a bilingual voice is used and
            no language code is specified, Amazon Polly uses the default language of the bilingual voice. The default language
            for any voice is the one returned by the DescribeVoices operation for the LanguageCode parameter. For example,
            if no language code is specified, Aditi will use Indian English rather than Hindi.
x-provenance:
  method: harvested
  publisher: Amazon Web Services
  source: https://raw.githubusercontent.com/aws/api-models-aws/3cd98287b471c106254abd89279cc87308d38bfd/models/polly/service/2016-06-10/polly-2016-06-10.json
  note: converted by smithy-to-openapi.py from AWS's Smithy model (roadmap#1001)