Multiverse Computing Audio API

openapi: 3.2.0
info:
  title: Chatbot Audio API
  description: Chatbot API. Provided by Multiverse Computing.
  contact:
    name: Multiverse Computing
    url: https://multiversecomputing.com/
    email: contact@multiversecomputing.com
  version: 0.1.1
servers:
- url: https://api.compactif.ai
  description: CompactifAI API production base URL (host the spec is served from; docs.compactif.ai documents this base)
tags:
- name: audio
paths:
  /v1/audio/transcriptions:
    post:
      tags:
      - audio
      summary: Audio transcriptions endpoint (OpenAI compatible)
      description: OpenAI-compatible POST `/v1/audio/transcriptions`.
      operationId: create_transcription_v1_audio_transcriptions_post
      security:
      - HTTPBearer: []
      parameters:
      - name: x-request-id
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-Request-Id
      - name: x-app-id
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: X-App-Id
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_create_transcription_v1_audio_transcriptions_post'
      responses:
        '200':
          description: Transcription response in the requested format
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    Body_create_transcription_v1_audio_transcriptions_post:
      properties:
        file:
          type: string
          contentMediaType: application/octet-stream
          title: File
          description: 'Audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Note: mp4, webm, and m4a files are automatically converted to mp3.'
        model:
          type: string
          title: Model
          description: Model identifier (e.g., whisper-1)
        prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: Prompt
          description: Optional text to guide the transcription
        response_format:
          anyOf:
          - type: string
            enum:
            - json
            - text
            - srt
            - verbose_json
            - vtt
          - type: 'null'
          title: Response Format
          description: Response format for the transcription. All values are accepted but will default to 'json'.
          default: json
        temperature:
          anyOf:
          - type: number
          - type: 'null'
          title: Temperature
          description: Sampling temperature between 0 and 1
        language:
          anyOf:
          - type: string
          - type: 'null'
          title: Language
          description: Language code hint for the audio (ISO-639-1, e.g. 'en', 'es'). If not provided, the model will auto-detect the language.
        stream:
          anyOf:
          - type: string
          - type: 'null'
          title: Stream
          description: If true, streams server-sent events.
        include:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Include
          description: Additional transcription metadata to return (e.g., 'logprobs'). Currently ignored by this service.
        timestamp_granularities:
          anyOf:
          - items:
              type: string
              enum:
              - word
              - segment
            type: array
          - type: 'null'
          title: Timestamp Granularities
          description: Timestamp granularity hints (word/segment). Ignored unless verbose JSON is supported.
        chunking_strategy:
          anyOf:
          - {}
          - type: 'null'
          title: Chunking Strategy
          description: Controls how audio is chunked (e.g., 'auto' or server_vad object). Ignored by this service.
      type: object
      required:
      - file
      - model
      title: Body_create_transcription_v1_audio_transcriptions_post
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer