Azure OpenAI Service Audio API

openapi: 3.1.0
info:
  title: Azure OpenAI Inference REST Audio API
  version: '2024-10-21'
  description: 'Data-plane REST API for running inference against models deployed to an

    Azure OpenAI resource. Endpoints follow the pattern

    `https://{resource-name}.openai.azure.com/openai/deployments/{deployment-id}/{endpoint}?api-version={api-version}`.


    Authenticate with an `api-key` header or with a Microsoft Entra ID bearer token

    (`Authorization: Bearer ...`, scope `https://cognitiveservices.azure.com/.default`).

    '
  contact:
    name: Azure OpenAI Service
    url: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference
servers:
- url: https://{resource-name}.openai.azure.com/openai
  description: Azure OpenAI resource endpoint
  variables:
    resource-name:
      default: my-resource
      description: Your Azure OpenAI resource name
tags:
- name: Audio
  description: Audio transcription and translation (Whisper)
paths:
  /deployments/{deployment-id}/audio/transcriptions:
    post:
      summary: Transcribe audio
      operationId: createTranscription
      tags:
      - Audio
      parameters:
      - in: path
        name: deployment-id
        required: true
        schema:
          type: string
      - in: query
        name: api-version
        required: true
        schema:
          type: string
          default: '2024-10-21'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - file
              properties:
                file:
                  type: string
                  format: binary
                language:
                  type: string
                prompt:
                  type: string
                response_format:
                  type: string
                  enum:
                  - json
                  - text
                  - srt
                  - verbose_json
                  - vtt
                temperature:
                  type: number
      responses:
        '200':
          description: Transcription
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
      security:
      - apiKey: []
      - entra: []
  /deployments/{deployment-id}/audio/translations:
    post:
      summary: Translate audio to English
      operationId: createTranslation
      tags:
      - Audio
      parameters:
      - in: path
        name: deployment-id
        required: true
        schema:
          type: string
      - in: query
        name: api-version
        required: true
        schema:
          type: string
          default: '2024-10-21'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - file
              properties:
                file:
                  type: string
                  format: binary
                prompt:
                  type: string
                response_format:
                  type: string
                  enum:
                  - json
                  - text
                  - srt
                  - verbose_json
                  - vtt
                temperature:
                  type: number
      responses:
        '200':
          description: Translation
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
      security:
      - apiKey: []
      - entra: []
components:
  securitySchemes:
    apiKey:
      type: apiKey
      in: header
      name: api-key
      description: Azure OpenAI resource API key
    entra:
      type: oauth2
      description: Microsoft Entra ID OAuth 2.0 bearer token
      flows:
        clientCredentials:
          tokenUrl: https://login.microsoftonline.com/common/oauth2/v2.0/token
          scopes:
            https://cognitiveservices.azure.com/.default: Azure Cognitive Services data plane