Modulate Velma 2 Stt Batch English Vfast API

openapi: 3.1.0
info:
  title: Velma 2 Accent Batch Velma 2 Stt Batch English Vfast API
  version: 0.0.0
  description: "Batch accent detection on an audio file via HTTP POST. Returns a single\nwhole-file accent label plus a time series of fixed-length windows, each\nwith its own accent label.\n\n## Behavior Notes\n- The `time_series` entries are consecutive, fixed-length windows over the\n  file; each entry's `start_ms` and `duration_ms` delimit its span. A\n  trailing remainder shorter than one full window is omitted.\n- A file shorter than one window returns an empty `time_series`; the\n  whole-file `accent` is still returned.\n- `accent` is always a non-null string.\n"
servers:
- url: https://platform.modulate.ai
  description: Modulate Accent Batch Server
security:
- ApiKeyAuth: []
tags:
- name: Velma 2 Stt Batch English Vfast
paths:
  /api/velma-2-stt-batch-english-vfast:
    post:
      operationId: transcribeEnglishVfast2
      summary: Transcribe an English audio file
      description: 'Accepts a single audio file and returns its full transcript as a

        synchronous JSON response.

        '
      security:
      - ApiKeyAuth: []
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - upload_file
              properties:
                upload_file:
                  type: string
                  format: binary
                  description: 'Audio file to transcribe. Must be non-empty. Supported formats:

                    `.aac`, `.aiff`, `.flac`, `.mov`, `.mp3`, `.mp4`, `.ogg`,

                    `.opus`, `.wav`, `.webm`. Maximum file size: 100 MB.

                    '
      responses:
        '200':
          description: Transcription completed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TranscriptionResponse'
              examples:
                short_audio:
                  summary: Short audio transcription
                  value:
                    text: Hello, how are you doing today?
                    duration_ms: 2000
                longer_audio:
                  summary: Longer audio with multiple sentences
                  value:
                    text: Welcome to today's meeting. We'll be discussing the quarterly results and planning for next quarter.
                    duration_ms: 14253
        '400':
          description: 'Bad request - the uploaded file is empty, its format is not supported, or the audio could not be decoded.

            '
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                invalid_format:
                  summary: Invalid file format
                  value:
                    detail: 'Unsupported file format. Supported formats: .aac, .aiff, .flac, .mov, .mp3, .mp4, .ogg, .opus, .wav, .webm.'
                empty_file:
                  summary: Empty file
                  value:
                    detail: The uploaded file is empty.
                unprocessable:
                  summary: Audio could not be decoded
                  value:
                    detail: The audio could not be processed. It may be corrupted or in an unsupported format.
                bad_value:
                  summary: Malformed request value
                  value:
                    detail: Invalid request.
        '403':
          description: Forbidden - the request is not permitted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: This request is not permitted.
        '422':
          description: 'Unprocessable entity - a required request parameter is missing or invalid (for example, the `X-API-Key` header or the `upload_file` field).

            '
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
        '429':
          description: Too many requests - the request could not be completed due to insufficient credits.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: Insufficient credits.
        '500':
          description: Internal server error during processing.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: Internal server error
        '502':
          description: Bad gateway - the request could not be validated.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: Unable to validate request. Please try again.
        '503':
          description: Service unavailable - the service is temporarily unavailable.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: The service is temporarily unavailable. Please try again later.
        '504':
          description: Gateway timeout - processing timed out.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: The request timed out. Please try again.
      tags:
      - Velma 2 Stt Batch English Vfast
components:
  schemas:
    TranscriptionResponse:
      type: object
      required:
      - text
      - duration_ms
      properties:
        text:
          type: string
          description: 'The complete transcribed text from the audio file. Text includes

            automatic capitalization and punctuation. May be an empty string

            if no speech was recognized.

            '
          example: Hello, how are you doing today?
        duration_ms:
          type: integer
          minimum: 0
          description: 'The total duration of the processed audio in milliseconds.

            '
          example: 14253
    HTTPValidationError:
      type: object
      properties:
        detail:
          type: array
          items:
            $ref: '#/components/schemas/ValidationError'
    ValidationError:
      type: object
      required:
      - loc
      - msg
      - type
      properties:
        loc:
          type: array
          items:
            anyOf:
            - type: string
            - type: integer
        msg:
          type: string
        type:
          type: string
    ErrorResponse:
      type: object
      required:
      - detail
      properties:
        detail:
          type: string
          description: Human-readable error message.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: API key used for authentication and usage tracking.