Modulate Velma 2 Language Detection Batch API

openapi: 3.1.0
info:
  title: Velma 2 Accent Batch Velma 2 Language 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 Language Detection Batch
paths:
  /api/velma-2-language-detection-batch:
    post:
      operationId: detectLanguageBatch
      summary: Identify the spoken language of an audio file
      description: 'Accepts a single audio file and returns the detected language 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 analyze. Must be non-empty. Supported formats:

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

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

                    '
      responses:
        '200':
          description: Language detection completed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/LanguageDetectionResponse'
              examples:
                english:
                  summary: English clip with high confidence
                  value:
                    predicted_language: English
                    predicted_language_code: en
                    confidence: 0.9847
                    duration_ms: 14253
                french:
                  summary: French clip
                  value:
                    predicted_language: French
                    predicted_language_code: fr
                    confidence: 0.9612
                    duration_ms: 8421
                lowConfidence:
                  summary: Low-confidence result
                  value:
                    predicted_language: Spanish
                    predicted_language_code: es
                    confidence: 0.4123
                    duration_ms: 5230
        '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
        '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 Language Detection Batch
components:
  schemas:
    HTTPValidationError:
      type: object
      properties:
        detail:
          type: array
          items:
            $ref: '#/components/schemas/ValidationError'
    LanguageDetectionResponse:
      type: object
      required:
      - predicted_language
      - predicted_language_code
      - confidence
      - duration_ms
      properties:
        predicted_language:
          type: string
          description: 'Human-readable language name (e.g. `"English"`, `"French"`, `"Mandarin"`). Suitable for display to end users.

            '
          example: English
        predicted_language_code:
          type: string
          description: 'Lowercase ISO 639-1 language code (e.g. `"en"`, `"fr"`, `"zh"`). Suitable for routing, locale switching, or BCP-47 tags.

            '
          example: en
        confidence:
          type: number
          format: double
          minimum: 0
          maximum: 1
          description: 'Probability associated with the predicted language, in the range 0.0-1.0. Higher means more confident.

            '
          example: 0.9847
        duration_ms:
          type: integer
          minimum: 0
          description: 'Total duration of the decoded audio in milliseconds. Note: only the first 30 seconds are analyzed regardless of this value.

            '
          example: 14253
    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.