> ## Documentation Index > Fetch the complete documentation index at: https://docs.modulate.ai/llms.txt > Use this file to discover all available pages before exploring further. # Deepfake Detection Batch > Detect synthetic (AI-generated) voice in a pre-recorded audio file. Returns per-frame deepfake scores. ## OpenAPI ````yaml api/velma_2_synthetic_voice_detection_batch.yaml POST /api/velma-2-synthetic-voice-detection-batch openapi: 3.1.0 info: title: Velma 2 Synthetic Voice Detection Batch API description: > Batch endpoint for detecting synthetic (AI-generated) speech in single-speaker audio files via HTTP POST. The audio is analysed as a sequence of windowed frames, each independently classified as synthetic, non-synthetic, or no-content (silence), returned in order across the full duration. ## Behavior Notes - Leading and trailing silence is excluded from analysis; frame timestamps still reflect positions in the original file. - Frames that contain only silence or no usable audio are assigned a `no-content` verdict with confidence `1.0`. - Files shorter than a single 4-second analysis window are still accepted and analysed. version: 0.0.0 servers: - url: https://platform.modulate.ai description: Modulate Synthetic Voice Detection Batch Server security: - ApiKeyAuth: [] paths: /api/velma-2-synthetic-voice-detection-batch: post: 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. operationId: detectSyntheticVoice 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. security: - ApiKeyAuth: [] components: schemas: 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 ErrorResponse: type: object required: - detail properties: detail: type: string description: Human-readable error message. HTTPValidationError: type: object properties: detail: type: array items: $ref: '#/components/schemas/ValidationError' 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 ValidationError: type: object required: - loc - msg - type properties: loc: type: array items: anyOf: - type: string - type: integer msg: type: string type: type: string securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-Key description: API key used for authentication and usage tracking. ````