openapi: 3.0.3
info:
  title: RingCentral Adaptive Cards Audio API
  description: RingCentral API specification
  version: 1.0.58-20240529-47eda8bd
  contact:
    name: RingCentral Developers Support
    url: https://developers.ringcentral.com/support
  termsOfService: https://www.ringcentral.com/legal/apilitos.html
  license:
    name: RingCentral API License Agreement
    url: https://www.ringcentral.com/legal/apilitos.html
servers:
- url: https://platform.ringcentral.com
  description: Production API entry point
- url: https://media.ringcentral.com
  description: Production Media entry point
- url: https://platform.devtest.ringcentral.com
  description: Developer sandbox API entry point
- url: https://platform.devtest.ringcentral.com
  description: Developer sandbox Media entry point
security:
- OAuth2: []
tags:
- name: Audio
  description: Conversational AI audio processing APIs
paths:
  /ai/audio/v1/enrollments:
    get:
      tags:
      - Audio
      summary: List Enrolled Speakers
      description: Returns the List of Enrolled Speakers
      operationId: caiEnrollmentsList
      parameters:
      - name: partial
        in: query
        description: Indicates if partially enrolled speakers should be returned
        required: true
        style: form
        explode: true
        schema:
          type: boolean
      - name: perPage
        in: query
        description: Number of enrollments to be returned per page
        required: true
        style: form
        explode: true
        schema:
          type: integer
          format: int32
      - name: page
        in: query
        description: Page number to be returned
        required: true
        style: form
        explode: true
        schema:
          type: integer
          format: int32
      responses:
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '200':
          description: List of enrolled speakers
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListEnrolledSpeakers'
      x-throttling-group: Heavy
      x-app-permission: AI
    post:
      tags:
      - Audio
      summary: Create Speaker Enrollment
      description: Creates Enrollment for the provided Speaker.
      operationId: caiEnrollmentsCreate
      requestBody:
        $ref: '#/components/requestBodies/EnrollmentRequest'
      responses:
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '409':
          description: The {speakerId} already exists
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '201':
          description: Enrollments Request Created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EnrollmentStatus'
      x-throttling-group: Heavy
      x-app-permission: AI
  /ai/audio/v1/enrollments/{speakerId}:
    get:
      tags:
      - Audio
      summary: Get Speaker Enrollment Status
      description: Get The Status of Enrollment for the provided Speaker.
      operationId: caiEnrollmentsGet
      parameters:
      - $ref: '#/components/parameters/SpeakerId'
      responses:
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '404':
          description: The {speakerId} doesn't exist
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '200':
          description: Fetch enrollment status for speaker {speakerId}
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EnrollmentStatus'
      x-throttling-group: Heavy
      x-app-permission: AI
    delete:
      tags:
      - Audio
      summary: Delete Speaker Enrollment
      description: Delete The Enrollment for the provided Speaker.
      operationId: caiEnrollmentsDelete
      parameters:
      - $ref: '#/components/parameters/SpeakerId'
      responses:
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '404':
          description: The speakerId wasn't enrolled
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '410':
          description: The speakerId doesn't exist, already deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '204':
          description: Enrollment deleted successfully
      x-throttling-group: Heavy
      x-app-permission: AI
    patch:
      tags:
      - Audio
      summary: Update Speaker Enrollment
      description: Add newer audio data to improve an existing speaker enrollment
      operationId: caiEnrollmentsUpdate
      parameters:
      - $ref: '#/components/parameters/SpeakerId'
      requestBody:
        $ref: '#/components/requestBodies/EnrollmentPatchRequest'
      responses:
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '404':
          description: The {speakerId} doesn't exist
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
        '201':
          description: Enrollments Request Created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EnrollmentStatus'
      x-throttling-group: Heavy
      x-app-permission: AI
  /ai/audio/v1/async/speech-to-text:
    post:
      tags:
      - Audio
      summary: Speech to Text Conversion
      description: Returns Speech to Text Conversion to the provided webhook URI.
      operationId: caiSpeechToText
      parameters:
      - $ref: '#/components/parameters/Webhook'
      requestBody:
        $ref: '#/components/requestBodies/AsrRequest'
      responses:
        '202':
          description: Task accepted for processing.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiAsyncApiResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
      callbacks:
        requestProcessed:
          '{$request.query.webhook}':
            post:
              parameters:
              - $ref: '#/components/parameters/CallbackRequestId'
              requestBody:
                $ref: '#/components/requestBodies/SpeechToTextCallbackRequest'
              responses:
                '200':
                  description: Callback successfully accepted
      x-throttling-group: Heavy
      x-app-permission: AI
  /ai/audio/v1/async/speaker-diarize:
    post:
      tags:
      - Audio
      summary: Speaker Diarization
      description: 'Identifies who said what. Speaker diarization will identify the speaker for each segment

        so you can tell who spoke the sentence, paragraph, or phrase.

        '
      operationId: caiSpeakerDiarize
      parameters:
      - $ref: '#/components/parameters/Webhook'
      requestBody:
        $ref: '#/components/requestBodies/DiarizeRequest'
      responses:
        '202':
          description: Task accepted for processing.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiAsyncApiResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
      callbacks:
        requestProcessed:
          '{$request.query.webhook}':
            post:
              parameters:
              - $ref: '#/components/parameters/CallbackRequestId'
              requestBody:
                $ref: '#/components/requestBodies/DiarizeCallbackRequest'
              responses:
                '200':
                  description: Callback successfully accepted
      x-throttling-group: Heavy
      x-app-permission: AI
  /ai/audio/v1/async/speaker-identify:
    post:
      tags:
      - Audio
      summary: Speaker Identification
      description: Returns Speaker Identification to the provided webhook URI.
      operationId: caiSpeakerIdentify
      parameters:
      - $ref: '#/components/parameters/Webhook'
      requestBody:
        $ref: '#/components/requestBodies/IdentifyRequest'
      responses:
        '202':
          description: Task accepted for processing.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiAsyncApiResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CaiErrorResponse'
      callbacks:
        requestProcessed:
          '{$request.query.webhook}':
            post:
              parameters:
              - $ref: '#/components/parameters/CallbackRequestId'
              requestBody:
                $ref: '#/components/requestBodies/SpeakerIdentifyCallbackRequest'
              responses:
                '200':
                  description: Callback successfully accepted
      x-throttling-group: Heavy
      x-app-permission: AI
components:
  parameters:
    SpeakerId:
      name: speakerId
      in: path
      description: Speaker identifier of enrolled speaker
      required: true
      style: simple
      explode: false
      schema:
        type: string
      example: JohnDoe
    CallbackRequestId:
      name: RCRequestId
      deprecated: true
      in: header
      description: 'Input RequestId corresponding to this response.\

        DEPRECATED. "jobId" body attribute should be used for tracking.

        '
      required: true
      style: simple
      explode: false
      schema:
        type: string
    Webhook:
      name: webhook
      in: query
      description: The webhook URI to which the job response will be returned
      required: true
      style: form
      explode: true
      schema:
        type: string
        format: uri
  schemas:
    TranscribedObject:
      required:
      - transcript
      - words
      type: object
      properties:
        speakerCount:
          type: integer
          description: The number of speakers detected. Field is set only when enableSpeakerDiarization is true.
          format: int32
          example: 2
        utterances:
          type: array
          description: Speaker wise utterances. Field is set only when enableSpeakerDiarization is true.
          items:
            $ref: '#/components/schemas/UtteranceObject'
        words:
          type: array
          items:
            $ref: '#/components/schemas/WordSegment'
        confidence:
          type: number
          description: Overall transcription confidence.
          format: float
        transcript:
          type: string
          description: The entire transcript with/without punctuations according to the input.
    WordSegment:
      required:
      - end
      - start
      - word
      type: object
      properties:
        speakerId:
          type: string
          example: JohnDoe
        start:
          type: number
          format: float
          example: 0.3
        end:
          type: number
          format: float
          example: 5.1
        confidence:
          type: number
          format: float
          example: 0.97
        word:
          type: string
          example: hello
    CaiErrorCodeResponse:
      required:
      - errorCode
      - message
      type: object
      properties:
        errorCode:
          type: string
          enum:
          - CAI-101
          - CAI-102
          - CAI-103
          - CAI-104
          - CAI-105
          - CAI-106
          - CAI-107
          - CAI-108
          - CAI-109
          - CAI-110
        message:
          type: string
          description: Helpful description of the errorCode
        parameterName:
          type: string
          description: Name of parameter if specified in the message
    PagingSchema:
      required:
      - page
      - perPage
      - totalPages
      type: object
      properties:
        page:
          type: integer
          format: int32
          example: 2
        totalPages:
          type: integer
          format: int32
          example: 10
        perPage:
          type: integer
          format: int32
          example: 5
    CaiAsyncApiResponse:
      type: object
      properties:
        jobId:
          type: string
    ContentInput:
      type: object
      properties:
        contentUri:
          type: string
          description: Publicly facing uri
          format: uri
    DiarizedObject:
      required:
      - speakerCount
      - utterances
      type: object
      properties:
        speakerCount:
          type: integer
          format: int32
          example: 2
        utterances:
          type: array
          items:
            $ref: '#/components/schemas/DiarizeSegment'
    DiarizeInput:
      allOf:
      - $ref: '#/components/schemas/AudioInput'
      - type: object
        properties:
          separateSpeakerPerChannel:
            type: boolean
            description: Set to True if the input audio is multi-channel and each channel has a separate speaker.
            example: false
          speakerCount:
            type: integer
            description: Number of speakers in the file, omit parameter if unknown
            format: int32
            example: 2
          speakerIds:
            type: array
            description: Optional set of speakers to be identified from the call.
            example:
            - speakerId1
            - speakerId2
            items:
              type: string
          enableVoiceActivityDetection:
            type: boolean
            description: Apply voice activity detection.
    SpeechContextPhrasesInput:
      required:
      - phrases
      type: object
      minItems: 1
      maxItems: 50
      properties:
        phrases:
          type: array
          description: Words or Phrases to boost
          example:
          - Mohit
          - Sushant
          - RingCentral
          items:
            type: string
    CaiErrorResponse:
      type: object
      properties:
        errors:
          type: array
          items:
            $ref: '#/components/schemas/CaiErrorCodeResponse'
    WordTimingsUnit:
      type: object
      properties:
        start:
          type: number
          format: float
          example: 0.3
        end:
          type: number
          format: float
          example: 5.1
        word:
          type: string
          example: Hello
    SpeakerIdentificationObject:
      required:
      - utterances
      type: object
      properties:
        utterances:
          type: array
          items:
            $ref: '#/components/schemas/DiarizeSegment'
    EnrollmentPatchInput:
      required:
      - content
      - encoding
      type: object
      properties:
        encoding:
          type: string
          description: The encoding of the original audio
          example: Wav
          enum:
          - Mpeg
          - Mp4
          - Wav
          - Webm
          - Webp
          - Aac
          - Avi
          - Ogg
        languageCode:
          type: string
          description: Language spoken in the audio file.
          example: en-US
        content:
          type: string
          description: Base64-encoded audio file data.
          example: base64EncodedAudioInput
    IdentifyInput:
      required:
      - speakerIds
      allOf:
      - $ref: '#/components/schemas/AudioInput'
      - type: object
        properties:
          speakerIds:
            type: array
            description: Set of enrolled speakers to be identified from the media.
            example:
            - speakerId1
            - speakerId2
            items:
              type: string
          enableVoiceActivityDetection:
            type: boolean
            description: Apply voice activity detection.
    DiarizeApiResponse:
      type: object
      properties:
        status:
          type: string
          enum:
          - Success
          - Fail
        response:
          oneOf:
          - $ref: '#/components/schemas/DiarizedObject'
          - $ref: '#/components/schemas/CaiErrorResponse'
    AsrApiResponse:
      type: object
      properties:
        status:
          type: string
          enum:
          - Success
          - Fail
        response:
          oneOf:
          - $ref: '#/components/schemas/TranscribedObject'
          - $ref: '#/components/schemas/CaiErrorResponse'
    UtteranceObject:
      required:
      - end
      - start
      - text
      type: object
      properties:
        start:
          type: number
          format: float
          example: 0.3
        end:
          type: number
          format: float
          example: 5.1
        text:
          type: string
          example: Hello! This is John.
        confidence:
          type: number
          format: float
          example: 0.97
        speakerId:
          type: string
          example: JohnDoe
        wordTimings:
          type: array
          items:
            $ref: '#/components/schemas/WordTimingsUnit'
    EnrollmentInput:
      required:
      - content
      - encoding
      - speakerId
      allOf:
      - $ref: '#/components/schemas/EnrollmentPatchInput'
      - type: object
        properties:
          speakerId:
            type: string
            description: The enrollment ID to be registered. Acceptable format [a-zA-Z0-9_]+
            example: JohnDoe
    ListEnrolledSpeakers:
      required:
      - paging
      - records
      type: object
      properties:
        paging:
          $ref: '#/components/schemas/PagingSchema'
        records:
          type: array
          items:
            $ref: '#/components/schemas/EnrollmentStatus'
    AudioInput:
      required:
      - encoding
      - languageCode
      allOf:
      - $ref: '#/components/schemas/ContentInput'
      - type: object
        properties:
          encoding:
            type: string
            description: The encoding of the original audio
            example: Wav
            enum:
            - Mpeg
            - Mp4
            - Wav
            - Webm
            - Webp
            - Aac
            - Avi
            - Ogg
          languageCode:
            type: string
            description: Language spoken in the audio file.
            example: en-US
          source:
            type: string
            description: 'Source of the audio file eg: Phone, RingCentral, GoogleMeet, Zoom etc'
            example: RingCentral
          audioType:
            type: string
            description: Type of the audio
            example: CallCenter
            enum:
            - CallCenter
            - Meeting
            - EarningsCalls
            - Interview
            - PressConference
            - Voicemail
    DiarizeSegment:
      required:
      - end
      - speakerId
      - start
      type: object
      properties:
        speakerId:
          type: string
          example: JohnDoe
        start:
          type: number
          format: float
          example: 0.3
        end:
          type: number
          format: float
          example: 5.1
        confidence:
          type: number
          format: float
          example: 0.97
    AsrInput:
      allOf:
      - $ref: '#/components/schemas/DiarizeInput'
      - type: object
        properties:
          enablePunctuation:
            type: boolean
            description: Enables Smart Punctuation API.
          enableSpeakerDiarization:
            type: boolean
            description: Tags each word corresponding to the speaker.
            default: false
          separateSpeakerPerChannel:
            type: boolean
            description: Indicates that the input audio is multi-channel and each channel has a separate speaker.
            default: false
          speechContexts:
            type: array
            description: Indicates the words/phrases that will be used for boosting the transcript. This can help to boost accuracy for cases like Person Names, Company names etc.
            items:
              $ref: '#/components/schemas/SpeechContextPhrasesInput'
    EnrollmentStatus:
      required:
      - enrollmentComplete
      - speakerId
      - totalSpeechDuration
      type: object
      properties:
        enrollmentQuality:
          type: string
          description: Quality of the enrollment.
          example: Average
          enum:
          - Poor
          - Average
          - Good
          - High
        enrollmentComplete:
          type: boolean
          description: Status of the enrollment.
          example: true
        speakerId:
          type: string
          example: JohnDoe
        totalEnrollDuration:
          type: number
          description: Total speech duration of the enrollment in seconds.
          format: float
          example: 20.1
        totalSpeechDuration:
          type: number
          description: Total duration of the enrollment in seconds.
          format: float
          example: 30.5
    SpeakerIdentifyApiResponse:
      type: object
      properties:
        status:
          type: string
          enum:
          - Success
          - Fail
        response:
          oneOf:
          - $ref: '#/components/schemas/SpeakerIdentificationObject'
          - $ref: '#/components/schemas/CaiErrorResponse'
  requestBodies:
    AsrRequest:
      description: Speech to Text API Input Format
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/AsrInput'
      required: true
    SpeechToTextCallbackRequest:
      description: Speech to Text API Callback Output
      content:
        application/json:
          schema:
            allOf:
            - type: object
              properties:
                jobId:
                  type: string
                creationTime:
                  type: string
                  format: date-time
                completionTime:
                  type: string
                  format: date-time
                expirationTime:
                  type: string
                  format: date-time
            - $ref: '#/components/schemas/AsrApiResponse'
      required: true
    EnrollmentPatchRequest:
      description: Patch Speaker Enrollment API Input Format
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/EnrollmentPatchInput'
      required: true
    DiarizeRequest:
      description: Speaker Diarization API Input Format
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/DiarizeInput'
      required: true
    EnrollmentRequest:
      description: Speaker Enrollment API Input Format
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/EnrollmentInput'
      required: true
    IdentifyRequest:
      description: Speaker Identification API Input Format
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/IdentifyInput'
      required: true
    SpeakerIdentifyCallbackRequest:
      description: Speaker Identification API Callback Output
      content:
        application/json:
          schema:
            allOf:
            - type: object
              properties:
                jobId:
                  type: string
                creationTime:
                  type: string
                  format: date-time
                completionTime:
                  type: string
                  format: date-time
                expirationTime:
                  type: string
                  format: date-time
            - $ref: '#/components/schemas/SpeakerIdentifyApiResponse'
      required: true
    DiarizeCallbackRequest:
      description: Speaker Diarization API Callback Output
      content:
        application/json:
          schema:
            allOf:
            - type: object
              properties:
                jobId:
                  type: string
                creationTime:
                  type: string
                  format: date-time
                completionTime:
                  type: string
                  format: date-time
                expirationTime:
                  type: string
                  format: date-time
            - $ref: '#/components/schemas/DiarizeApiResponse'
      required: true
  securitySchemes:
    OAuth2:
      type: oauth2
      flows:
        authorizationCode:
          authorizationUrl: https://platform.ringcentral.com/restapi/oauth/authorize
          tokenUrl: https://platform.ringcentral.com/restapi/oauth/token
          refreshUrl: https://platform.ringcentral.com/restapi/oauth/token
          scopes: {}
x-tagGroups:
- name: Voice
  popular: true
  tags:
  - Business Hours
  - Call Blocking
  - Call Control
  - Call Forwarding
  - Call Handling Rules
  - Interaction Rules
  - State-based Rules
  - Call Flip
  - Call Log
  - Call History
  - Call Log Export
  - Call Monitoring Groups
  - Call Queues
  - Call Recordings
  - Call Recording Settings
  - Device SIP Registration
  - Greetings
  - IVR
  - RingOut
  - Verification Calls
- name: SMS and Fax
  popular: true
  tags:
  - Fax
  - Message Exports
  - Message Store
  - Pager Messages
  - SMS
  - High Volume SMS
  - SMS Log Export
  - SMS Templates
  - Voicemail Broadcasting
- name: Social Messaging
  popular: true
  tags:
  - Identities
  - Contents
- name: Team Messaging
  popular: true
  tags:
  - Adaptive Cards
  - Bots
  - Calendar Events
  - Chats
  - Conversations
  - Compliance Exports
  - Contacts
  - Incoming Webhooks
  - Notes
  - Posts
  - Profile
  - Tasks
  - Teams
- name: Video
  popular: true
  tags:
  - Bridge Management
  - Delegation Management
  - Meetings History
  - Meeting Recordings
  - RCM Meetings (Legacy)
  - RCM Webinars (Legacy)
- name: Webinar
  popular: true
  tags:
  - Webinars and Sessions
  - Invitees
  - Historical Webinars
  - Historical Recordings
  - Registration Management
  - Registrants
  - Webinar Analytics
  - Webinar Subscriptions
- name: Analytics
  popular: true
  tags:
  - Business Analytics
- name: Artificial Intelligence
  popular: true
  tags:
  - Insights
  - Audio
  - Text
  - Status
- name: Authentication
  tags:
  - OAuth 2.0 / OpenID Connect
  - Interoperability
- name: Account
  tags:
  - Company
  - Custom Fields
  - Features
  - Licenses
  - Tax Locations
  - Cost Centers
  - Multi-Site
  - Phone Numbers
  - Presence
  - Regional Settings
  - User Permissions
  - User Settings
  - Audit Trail
  - Calling Rates
  - Appearance Customization
  - Account Integrations
- name: Provisioning
  tags:
  - Automatic Location Updates
  - Devices
  - Extensions
  - Paging Only Groups
  - Park Locations
  - Phone Lines
  - SCIM
  - Shared Lines
  - Group Call Pickup
  - Delegated Lines Groups
  - Directed Call Pickup
  - IVR Apps
  - Video Configuration
  - Number Porting
  - SMB
  - Account Federation
  - Integrations
  - Enterprise Portal API
  - Push to Talk Provisioning
  - BYOC
- name: Address Book
  tags:
  - External Contacts
  - Internal Contacts
  - Hybrid Directory Contacts
  - Overlay Contacts
  - External Shared Directory
- name: Roles and Permissions
  tags:
  - Permissions
  - Role Management
  - Site Administration
  - User Groups
- name: Events & Notifications
  tags:
  - Subscriptions
- name: User Integrations
  tags:
  - Token Management
  - Calendar Management
  - Calendar Event Management
  - Calendar Presence Link
  - Cloud Personal Contacts
  - Cloud Shared Contacts
  - Cloud Directory
  - Deprecated Calendar API
- name: Rooms
  tags:
  - Rooms Client API
  - Rooms Management API
- name: App Management
  tags:
  - App Gallery
  - App Rating Review
  - Bot Provisioning
- name: Workflow Builder
  tags:
  - Flows
  - Flow Editor
  - Flow Log
  - Flow Templates
- name: Utilities
  tags:
  - API Info
  - Application Settings
  - Async Tasks
  - User Notifications
  - Client Versions
  - End-to-End Encryption