Analyze an audio file
Analyze an audio file. By default (`input.WorkflowType` 4) this detects whether a voice is AI-generated or cloned; other workflows transcribe speech, run intelligence analysis, or combine both. Max 50 MB per file; formats `wav`, `mp3`, `flac`, `m4a`, `opus`.
Authorization
BearerAuth Send your secret API token as a bearer token in the Authorization header:
Authorization: Bearer <token>. Keep it server-side and never expose it in client code.
In: header
Request Body
multipart/form-data
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
{
"isSuccessful": true,
"errorMessage": null,
"workflowType": 4,
"transcript": null,
"analysis": null,
"contextUsed": null,
"isAiDetected": true,
"detectionConfidence": 0.93,
"detectionClassification": "fake",
"processingTimeMs": 2110,
"creditsUsed": 1,
"metadata": null
}{
"error": {
"code": "IMAGE_FORENSICS:FILE_TOO_LARGE",
"message": "File photo.jpg exceeds the maximum size of 50 MB."
}
}{
"error": {
"code": "IMAGE_FORENSICS:UNSUPPORTED_FORMAT",
"message": "Unsupported file format. Allowed — jpg, jpeg, png, webp, heic, heif, tiff."
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "Invalid or missing API token."
}
}
