Modulate Velma 2 Synthetic Voice Detection Batch API

openapi: 3.1.0
info:
  title: Velma 2 Accent Batch Velma 2 Synthetic Voice Detection Batch 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 Synthetic Voice Detection Batch
paths:
  /api/velma-2-synthetic-voice-detection-batch:
    post:
      operationId: detectSyntheticVoice
      summary: Detect synthetic voice in an audio file
      description: 'Accepts a single audio file and returns a per-frame synthetic-voice

        classification across the clip as a synchronous JSON response.

        Recommended audio length: 4-60 seconds; files shorter than 0.5 seconds

        are rejected with a 422.

        '
      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 analyse. Must be non-empty. Supported formats:

                    `.3gp`, `.3gpp`, `.aac`, `.aiff`, `.amr`, `.au`, `.flac`,

                    `.m4a`, `.mov`, `.mp3`, `.mp4`, `.ogg`, `.opus`, `.wav`,

                    `.webm`, `.wma`. Maximum file size: 100 MB.

                    '
      responses:
        '200':
          description: Detection completed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DetectionAPIResponse'
        '400':
          description: Bad request - the uploaded file is empty or its format is not supported.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                invalid_format:
                  summary: Invalid file format
                  value:
                    detail: 'Unsupported file format. Supported formats: .3gp, .3gpp, .aac, .aiff, .amr, .au, .flac, .m4a, .mov, .mp3, .mp4, .ogg, .opus, .wav, .webm, .wma.'
                empty_file:
                  summary: Empty file
                  value:
                    detail: The uploaded file is empty.
                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 - the audio is too short to analyze, could not

            be processed, or a required request parameter is missing or invalid

            (for example, the `X-API-Key` header or the `upload_file` field).

            '
          content:
            application/json:
              schema:
                oneOf:
                - $ref: '#/components/schemas/ErrorResponse'
                - $ref: '#/components/schemas/HTTPValidationError'
              examples:
                audio_too_short:
                  summary: Audio too short
                  value:
                    detail: The audio is too short to analyze.
                audio_unprocessable:
                  summary: Audio could not be processed
                  value:
                    detail: The audio could not be processed. It may be corrupted or in an unsupported format.
        '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 inference.
          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.
        '504':
          description: Gateway timeout - inference did not complete in time.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                detail: The request timed out. Please try again.
      tags:
      - Velma 2 Synthetic Voice Detection Batch
components:
  schemas:
    ValidationError:
      type: object
      required:
      - loc
      - msg
      - type
      properties:
        loc:
          type: array
          items:
            anyOf:
            - type: string
            - type: integer
        msg:
          type: string
        type:
          type: string
    HTTPValidationError:
      type: object
      properties:
        detail:
          type: array
          items:
            $ref: '#/components/schemas/ValidationError'
    ErrorResponse:
      type: object
      required:
      - detail
      properties:
        detail:
          type: string
          description: Human-readable error message.
    FrameResult:
      type: object
      required:
      - start_time_ms
      - end_time_ms
      - verdict
      - confidence
      properties:
        start_time_ms:
          type: integer
          minimum: 0
          description: Frame start time in milliseconds.
          example: 0
        end_time_ms:
          type: integer
          minimum: 0
          description: Frame end time in milliseconds.
          example: 3000
        verdict:
          type: string
          enum:
          - synthetic
          - non-synthetic
          - no-content
          description: 'Classification for this frame:

            - `synthetic` - the frame likely contains AI-generated speech.

            - `non-synthetic` - the frame likely contains natural human speech.

            - `no-content` - the frame is silent or contains no usable audio.

            '
          example: synthetic
        confidence:
          type: number
          format: double
          minimum: 0
          maximum: 1
          description: Confidence in the stated verdict, from 0 (lowest) to 1 (highest).
          example: 0.9732
    DetectionAPIResponse:
      type: object
      required:
      - filename
      - frames
      - duration_ms
      properties:
        filename:
          oneOf:
          - type: string
          - type: 'null'
          description: Original filename of the uploaded audio.
          example: recording.wav
        frames:
          type: array
          description: Ordered list of per-frame detection results covering the full audio duration.
          items:
            $ref: '#/components/schemas/FrameResult'
        duration_ms:
          type: integer
          minimum: 0
          description: Total duration of the audio in milliseconds.
          example: 34500
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: API key used for authentication and usage tracking.