Create Transcription

Upload an audio file and receive a structured JSON response with transcription, speaker diarization, and AI analysis in a single synchronous API call.

POST/v1/transcribe

Request

Send a multipart/form-data request with the audio file and optional parameters:

Field	Type	Required	Description
`audio`	File	Yes	Audio file (MP3, WAV, M4A, FLAC, OGG, WebM). Max 95 MB
`language`	String	No	ISO 639-1 code (e.g., "en"). Auto-detected if omitted
`mode`	String	No	`full` (default) or `fast`. Fast skips AI analysis
`redact_pii`	Boolean	No	Mask PII in transcript (names, SSNs, card numbers)
`instructions`	String	No	Custom AI prompt. Max 2,000 chars. See Custom Instructions

Example

curl

curl -X POST https://api.voxparse.com/v1/transcribe \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "[email protected]" \
  -F "language=en"

Response

Returns a JSON object with the transcript, segments with timestamps, word-level timing, and an ai_analysis object containing sentiment, compliance, financial data, and more.

Tip: Use mode=fast for transcription-only jobs that do not need AI analysis. This reduces processing time and cost.

For the complete response schema, see the Full API Reference.