Features

Medical Mode

Tune transcription for clinical vocabulary: drug names, procedures, anatomy, and medical shorthand.

Medical Mode tunes recognition for clinical speech: medication names, procedures, anatomy, and the shorthand used in dictations and consultations. Enable it with medical_mode: true on the create request. There is no extra charge; you pay the normal model rate.

Quickstart

bash

curl -s -X POST https://api.realtimevoicekit.com/v2/transcripts \
  -H "Authorization: Bearer rtvk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://example.com/dictation.mp3",
    "language_code": "en",
    "medical_mode": true
  }'

Supported languages

Medical Mode is available in English (en), Spanish (es), German (de), and French (fr), and requires an explicit language_code. With auto-detection or any other language, the flag is ignored and the transcript still runs as a standard job; the request never fails because of an unsupported Medical Mode combination.

Combine medical_mode with keyterms_prompt for clinic-specific vocabulary such as practitioner names or local product names. See Keyterms Prompting.