Variants for response for `/audio/transcriptions` missing discriminator field.

[glecaros]

The response for /audio/transcription defines a discriminated union with task being the discriminated property. Of the three variants, only CreateTranscriptionResponseDiarizedJson has this property.

The definitions:

/audio/transcriptions:
  post:
    operationId: createTranscription
    tags:
      - Audio
    summary: Create transcription
    requestBody:
      required: true
      content:
        multipart/form-data:
          schema:
            $ref: '#/components/schemas/CreateTranscriptionRequest'
    responses:
      '200':
        description: OK
        content:
          application/json:
            schema:
              anyOf:
                - $ref: '#/components/schemas/CreateTranscriptionResponseJson'
                - $ref: '#/components/schemas/CreateTranscriptionResponseDiarizedJson'
                  x-stainless-skip:
                    - go
                - $ref: '#/components/schemas/CreateTranscriptionResponseVerboseJson'
              discriminator:
                propertyName: task
          text/event-stream:
            schema:
              $ref: '#/components/schemas/CreateTranscriptionResponseStreamEvent'

CreateTranscriptionResponseJson:
  type: object
  description: Represents a transcription response returned by model, based on the provided input.
  properties:
    text:
      type: string
      description: The transcribed text.
    logprobs:
      type: array
      optional: true
      description: >
        The log probabilities of the tokens in the transcription. Only returned with the models
        `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array.
      items:
        type: object
        properties:
          token:
            type: string
            description: The token in the transcription.
          logprob:
            type: number
            description: The log probability of the token.
          bytes:
            type: array
            items:
              type: number
            description: The bytes of the token.
    usage:
      type: object
      description: Token usage statistics for the request.
      anyOf:
        - $ref: '#/components/schemas/TranscriptTextUsageTokens'
          title: Token Usage
        - $ref: '#/components/schemas/TranscriptTextUsageDuration'
          title: Duration Usage
      discriminator:
        propertyName: type
  required:
    - text

CreateTranscriptionResponseDiarizedJson:
  type: object
  description: >
    Represents a diarized transcription response returned by the model, including the combined transcript
    and speaker-segment annotations.
  properties:
    task:
      type: string
      description: The type of task that was run. Always `transcribe`.
      enum:
        - transcribe
      x-stainless-const: true
    duration:
      type: number
      description: Duration of the input audio in seconds.
    text:
      type: string
      description: The concatenated transcript text for the entire audio input.
    segments:
      type: array
      description: Segments of the transcript annotated with timestamps and speaker labels.
      items:
        $ref: '#/components/schemas/TranscriptionDiarizedSegment'
    usage:
      type: object
      description: Token or duration usage statistics for the request.
      discriminator:
        propertyName: type
      anyOf:
        - $ref: '#/components/schemas/TranscriptTextUsageTokens'
          title: Token Usage
        - $ref: '#/components/schemas/TranscriptTextUsageDuration'
          title: Duration Usage

CreateTranscriptionResponseVerboseJson:
  type: object
  description: Represents a verbose json transcription response returned by model, based on the provided input.
  properties:
    language:
      type: string
      description: The language of the input audio.
    duration:
      type: number
      description: The duration of the input audio.
    text:
      type: string
      description: The transcribed text.
    words:
      type: array
      description: Extracted words and their corresponding timestamps.
      items:
        $ref: '#/components/schemas/TranscriptionWord'
    segments:
      type: array
      description: Segments of the transcribed text and their corresponding details.
      items:
        $ref: '#/components/schemas/TranscriptionSegment'
    usage:
      $ref: '#/components/schemas/TranscriptTextUsageDuration'
  required:
    - language
    - duration
    - text