Microsoft Azure Audio API

openapi: 3.2.0
info:
  title: Microsoft Azure Azure OpenAI Service Audio API
  description: Azure OpenAI Service provides REST API access to OpenAI's language models including GPT-4, GPT-4 Turbo, GPT-3.5-Turbo, and the Embeddings model series. These models can be adapted to tasks including content generation, summarization, semantic search, and natural language to code translation. Users access the service through REST APIs, Python SDK, or the web-based interface in the Azure AI Foundry portal.
  version: '2024-06-01'
  contact:
    name: Microsoft Azure Support
    url: https://azure.microsoft.com/en-us/support/
    email: azuresupport@microsoft.com
  license:
    name: Microsoft API License
    url: https://learn.microsoft.com/en-us/legal/
  x-logo:
    url: https://azure.microsoft.com/svghandler/azure-logo.png
servers:
- url: https://{endpoint}/openai
  description: Azure OpenAI Service endpoint
  variables:
    endpoint:
      default: your-resource-name.openai.azure.com
      description: 'The Azure OpenAI resource endpoint. Format: https://{resource-name}.openai.azure.com'
security:
- apiKey: []
- oauth2:
  - https://cognitiveservices.azure.com/.default
tags:
- name: Audio
  description: Operations for audio transcription and translation
paths:
  /deployments/{deployment-id}/audio/transcriptions:
    post:
      operationId: AudioTranscriptions_Create
      summary: Microsoft Azure Create Audio Transcription
      description: Transcribes audio into the input language using the Whisper model.
      tags:
      - Audio
      parameters:
      - $ref: '#/components/parameters/DeploymentIdParameter'
      - $ref: '#/components/parameters/ApiVersionParameter'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/CreateTranscriptionRequest'
            examples:
              AudiotranscriptionsCreateRequestExample:
                summary: Default AudioTranscriptions_Create request
                x-microcks-default: true
                value:
                  file: example_value
                  language: example_value
                  prompt: example_value
                  response_format: json
                  temperature: 42.5
      responses:
        '200':
          description: Successfully transcribed the audio.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AudioTranscriptionResponse'
              examples:
                AudiotranscriptionsCreate200Example:
                  summary: Default AudioTranscriptions_Create 200 response
                  x-microcks-default: true
                  value:
                    text: example_value
        default:
          description: An error occurred.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                AudiotranscriptionsCreatedefaultExample:
                  summary: Default AudioTranscriptions_Create default response
                  x-microcks-default: true
                  value:
                    error:
                      code: example_value
                      message: example_value
                      param: example_value
                      type: example_value
                      inner_error:
                        code: example_value
                        content_filter_result: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /deployments/{deployment-id}/audio/translations:
    post:
      operationId: AudioTranslations_Create
      summary: Microsoft Azure Create Audio Translation
      description: Translates audio into English text using the Whisper model.
      tags:
      - Audio
      parameters:
      - $ref: '#/components/parameters/DeploymentIdParameter'
      - $ref: '#/components/parameters/ApiVersionParameter'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/CreateTranslationRequest'
            examples:
              AudiotranslationsCreateRequestExample:
                summary: Default AudioTranslations_Create request
                x-microcks-default: true
                value:
                  file: example_value
                  prompt: example_value
                  response_format: json
                  temperature: 42.5
      responses:
        '200':
          description: Successfully translated the audio.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AudioTranslationResponse'
              examples:
                AudiotranslationsCreate200Example:
                  summary: Default AudioTranslations_Create 200 response
                  x-microcks-default: true
                  value:
                    text: example_value
        default:
          description: An error occurred.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                AudiotranslationsCreatedefaultExample:
                  summary: Default AudioTranslations_Create default response
                  x-microcks-default: true
                  value:
                    error:
                      code: example_value
                      message: example_value
                      param: example_value
                      type: example_value
                      inner_error:
                        code: example_value
                        content_filter_result: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /deployments/{deployment-id}/audio/speech:
    post:
      operationId: AudioSpeech_Create
      summary: Microsoft Azure Create Speech From Text
      description: Generates audio from the input text.
      tags:
      - Audio
      parameters:
      - $ref: '#/components/parameters/DeploymentIdParameter'
      - $ref: '#/components/parameters/ApiVersionParameter'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateSpeechRequest'
            examples:
              AudiospeechCreateRequestExample:
                summary: Default AudioSpeech_Create request
                x-microcks-default: true
                value:
                  model: tts-1
                  input: example_value
                  voice: alloy
                  response_format: mp3
                  speed: 42.5
      responses:
        '200':
          description: Successfully generated speech audio.
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
              examples:
                AudiospeechCreate200Example:
                  summary: Default AudioSpeech_Create 200 response
                  x-microcks-default: true
                  value: example_value
        default:
          description: An error occurred.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                AudiospeechCreatedefaultExample:
                  summary: Default AudioSpeech_Create default response
                  x-microcks-default: true
                  value:
                    error:
                      code: example_value
                      message: example_value
                      param: example_value
                      type: example_value
                      inner_error:
                        code: example_value
                        content_filter_result: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    CreateTranslationRequest:
      type: object
      description: Request body for creating an audio translation.
      properties:
        file:
          type: string
          format: binary
          description: The audio file object to translate.
          example: example_value
        prompt:
          type: string
          description: An optional text to guide the model.
          example: example_value
        response_format:
          type: string
          enum:
          - json
          - text
          - srt
          - verbose_json
          - vtt
          default: json
          description: The format of the transcript output.
          example: json
        temperature:
          type: number
          default: 0
          description: The sampling temperature, between 0 and 1.
          example: 42.5
      required:
      - file
    AudioTranscriptionResponse:
      type: object
      description: Response from audio transcription.
      properties:
        text:
          type: string
          description: The transcribed text.
          example: example_value
      required:
      - text
    CreateSpeechRequest:
      type: object
      description: Request body for generating speech from text.
      properties:
        model:
          type: string
          description: The TTS model to use.
          enum:
          - tts-1
          - tts-1-hd
          example: tts-1
        input:
          type: string
          maxLength: 4096
          description: The text to generate audio for.
          example: example_value
        voice:
          type: string
          enum:
          - alloy
          - echo
          - fable
          - onyx
          - nova
          - shimmer
          description: The voice to use when generating the audio.
          example: alloy
        response_format:
          type: string
          enum:
          - mp3
          - opus
          - aac
          - flac
          default: mp3
          description: The format to audio in.
          example: mp3
        speed:
          type: number
          minimum: 0.25
          maximum: 4.0
          default: 1.0
          description: The speed of the generated audio.
          example: 42.5
      required:
      - model
      - input
      - voice
    ErrorResponse:
      type: object
      description: Error response.
      properties:
        error:
          type: object
          description: The error object.
          properties:
            code:
              type: string
              description: The error code.
            message:
              type: string
              description: The error message.
            param:
              type: string
              description: The parameter that caused the error.
            type:
              type: string
              description: The error type.
            inner_error:
              type: object
              description: Inner error details.
              properties:
                code:
                  type: string
                  description: The inner error code.
                content_filter_result:
                  type: object
                  description: Content filter results, if applicable.
          required:
          - code
          - message
          example: example_value
    AudioTranslationResponse:
      type: object
      description: Response from audio translation.
      properties:
        text:
          type: string
          description: The translated text.
          example: example_value
      required:
      - text
    CreateTranscriptionRequest:
      type: object
      description: Request body for creating an audio transcription.
      properties:
        file:
          type: string
          format: binary
          description: 'The audio file object to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.'
          example: example_value
        language:
          type: string
          description: The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
          example: example_value
        prompt:
          type: string
          description: An optional text to guide the model's style or continue a previous audio segment.
          example: example_value
        response_format:
          type: string
          enum:
          - json
          - text
          - srt
          - verbose_json
          - vtt
          default: json
          description: The format of the transcript output.
          example: json
        temperature:
          type: number
          default: 0
          description: The sampling temperature, between 0 and 1.
          example: 42.5
      required:
      - file
  parameters:
    DeploymentIdParameter:
      name: deployment-id
      in: path
      required: true
      description: The deployment ID of the model to use for this request.
      schema:
        type: string
    ApiVersionParameter:
      name: api-version
      in: query
      required: true
      description: The API version to use for this operation.
      schema:
        type: string
        default: '2024-06-01'
  securitySchemes:
    apiKey:
      type: apiKey
      name: api-key
      in: header
      description: Azure OpenAI API key authentication.
    oauth2:
      type: oauth2
      flows:
        implicit:
          authorizationUrl: https://login.microsoftonline.com/common/oauth2/v2.0/authorize
          scopes:
            https://cognitiveservices.azure.com/.default: Access Azure OpenAI