Transcribe

Transcribe an audio file to text using OVHcloud Whisper. Supports mp3, mp4, mpeg, mpga, m4a, wav, and webm formats up to 25 MB.

POSThttps://api.marinahealth.eu/ai/transcribe

Requires AuthVerified Email Requiredmultipart/form-dataRate limit: 500 requests per hour

Headers

Name	Type	Required	Description
Authorization	string	required	Bearer <accessToken>

Request Body

Body Parameters

Name	Type	Required	Description
audio	File	required	Audio file. Allowed MIME types: audio/mpeg, audio/mp4, audio/wav, audio/x-wav, audio/webm, audio/ogg, audio/m4a, audio/x-m4a. Max 25 MB.
language	string	optional	BCP-47 language hint (e.g. "en", "fr"). Optional — Whisper auto-detects if omitted.

Example Request

cURL

curl -X POST https://api.marinahealth.eu/ai/transcribe \
  -H "Authorization: Bearer <accessToken>" \
  -F "audio=@consultation.mp3" \
  -F "language=en"

Response

Successful

Field	Type	Description
transcription	string	Full transcribed text.

json

{
  "transcription": "The patient reports persistent lower back pain for three weeks..."
}