Vonage Audio Connector API

openapi: 3.2.0
info:
  title: Vonage Audio Connector API
  version: 0.3.2
  contact:
    name: Vonage DevRel
    url: https://developer.vonage.com
    email: devlre@vonage.com
  x-metaDescription: Get started with the Vonage Video API, a powerful tool for automating video communications. Learn more in Vonage's API documentation.
  x-metaTitle: Vonage Video API for Developers | Vonage API Documentation
  description: 'Operations tagged Audio Connector across 2 of this provider''s published API definitions: vonage-video-openapi.json, vonage-video-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://video.api.vonage.com
  description: Vonage Video
security:
- Vonage-JWT: []
tags:
- name: Audio Connector
  description: APIs relating to audio connector
paths:
  /v2/project/{application_id}/connect:
    parameters:
    - $ref: '#/components/parameters/application_id'
    post:
      tags:
      - Audio Connector
      summary: Start an audio connector connection
      description: Use this method to send audio from a Vonage Video API session to a WebSocket.
      operationId: start-audio-connector-connection
      requestBody:
        $ref: '#/components/requestBodies/Start-Audio-Connector'
      responses:
        '200':
          $ref: '#/components/responses/Audio-Connector-Started'
        '403':
          description: Forbidden
        '409':
          description: Live captions have already been started for this session
        '500':
          description: Vonage Video API Platform error
    servers:
    - url: https://video.api.vonage.com
      description: Vonage Video
components:
  parameters:
    application_id:
      name: application_id
      in: path
      required: true
      schema:
        type: string
      description: Vonage Application UUID
  schemas:
    Start-Audio-Connector:
      type: object
      properties:
        sessionId:
          type: string
          description: The Vonage Video session ID that includes the Vonage Video streams you want to include in the WebSocket stream. The Audio Connector feature is only supported in routed sessions
          example: 12312312-3811-4726-b508-e41a0f96c68f
        token:
          type: string
          description: A valid Vonage Video token for the Audio Connector connection to the Vonage Video Session. You can add additional data to the JWT to identify that the connection is the Audio Connector endpoint or for any other identifying data.
          example: eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJpYXQiOjE2OTkwNDMxMTEsImV4cCI6MTY5OTA2NDcxMSwianRpIjoiMW1pODlqRk9meVpRIiwiYXBwbGljYXRpb25faWQiOiIxMjMxMjMxMi0zODExLTQ3MjYtYjUwOC1lNDFhMGY5NmM2OGYiLCJzdWIiOiJ2aWRlbyIsImFjbCI6IiJ9.o3U506EejsS8D5Tob90FG1NC1cR69fh3pFOpxnyTHVFfgqI6NWuuN8lEwrS3Zb8bGxE_A9LyyUZ2y4uqLpyXRw
        websocket:
          type: object
          properties:
            uri:
              type: string
              description: A publicly reachable WebSocket URI to be used for the destination of the audio stream
              example: wss://example.com/ws-endpoint
            streams:
              type: array
              description: An array of stream IDs for the Vonage Video streams you want to include in the WebSocket audio. If you omit this property, all streams in the session will be included.
              items:
                type: string
              example:
              - streamId-1
              - streamId-2
            headers:
              type: object
              description: An object of key-value pairs of headers to be sent to your WebSocket server with each message, with a maximum length of 512 bytes.
              additionalProperties:
                type: string
            audioRate:
              type: number
              description: A number representing the audio sampling rate in Hz.
              example: 8000
              enum:
              - 8000
              - 16000
              - 24000
            bidirectional:
              type: boolean
              description: Whether to send audio data from the WebSocket connection to a stream published in the session. For more information see the [Audio Connector documentation](video/guides/audio-connector).
              default: false
            audioTransport:
              type: object
              description: A JSON object that configures how audio is serialized on the WebSocket wire. By default, audio is sent as raw binary PCM 16-bit frames.
              properties:
                transport:
                  type: string
                  description: '''binary'' (raw PCM16, the default) or ''json''.'
                  enum:
                  - binary
                  - json
                encoding:
                  type: string
                  description: Required when transport is 'json'. Set to 'base64'.
                  enum:
                  - base64
                audio_field:
                  type: string
                  description: The JSON key for the outbound audio data. Defaults to 'audio'.
                receive_audio_field:
                  type: string
                  description: The JSON key for inbound audio data (when bidirectional is enabled). Defaults to the same value as audio_field.
                static_fields:
                  type: object
                  description: An object of extra key-value pairs included in every outbound JSON audio message.
              if:
                required:
                - transport
                properties:
                  transport:
                    const: json
              then:
                required:
                - encoding
          required:
          - uri
      required:
      - sessionId
      - token
      - websocket
  responses:
    Audio-Connector-Started:
      description: Information about the audio connector session that was started
      content:
        application/json:
          schema:
            type: object
            properties:
              id:
                type: string
                description: A unique ID identifying the Audio Connector WebSocket connection.
                example: b0a5a8c7-dc38-459f-a48d-a7f2008da853
              captionsId:
                type: string
                description: Unique ID of the audio captioning session
                example: 7c0680fc-6274-4de5-a66f-d0648e8d3ac2
            required:
            - id
            - captionsId
  requestBodies:
    Start-Audio-Connector:
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Start-Audio-Connector'
  securitySchemes:
    Vonage-JWT:
      type: http
      scheme: bearer
      bearerFormat: JWT
x-refined-from:
- vonage-video-openapi.json
- vonage-video-openapi.yml
x-errors:
  validation:
    description: The provided payload is invalid
    resolution: 'Modify your request to provide a valid payload.

      * Minimum 8 characters

      * Maximum 25 characters

      * Minimum 1 lower case character

      * Minimum 1 upper case character

      * Minimum 1 digit

      '
    link:
      text: View API reference
      url: /api/account#createAPISecret
  delete-last-secret:
    description: You can not delete your only API secret
    resolution: Add another API secret before deleting this one