Nova-3 Medical overview
Nova-3 Medical by Deepgram
Optimized for healthcare environments: accurately recognizes drug names, diagnoses, procedures, and medical jargon in real-time and batch transcription.
Nova-3 Medical specs
- Model ID
deepgram/nova-3-medical- Developer
- Deepgram
- Input
- Audio
- Output
- Text
- Endpoint
POST https://api.aimlapi.com/v1/stt/create
Deepgram Nova-3 Medical is a domain-specialized variant of Nova-3, fine-tuned on clinical and healthcare audio datasets. It delivers significantly higher accuracy for medical terminology, prescription names, diagnoses, procedures, anatomical terms, making it the optimal choice for clinical documentation, telehealth platforms, EHR integrations, and medical dictation tools.
Performance Benchmarks
- Significantly lower word error rate on medical terminology vs. general-purpose models.
- Accurately recognizes drug names, ICD-10 diagnoses, and procedural terms.
- Real-time streaming with sub-300ms latency for live clinical workflows.
- Handles noisy clinical environments: background equipment sounds, phone audio.
- Designed to reduce manual review burden in medical documentation.
Architecture Breakdown
Nova-3 Medical is built on the same end-to-end deep learning engine as Nova-3, with an additional fine-tuning stage on curated medical audio corpora. The model's vocabulary and language model are biased toward clinical terminology, enabling reliable transcription of complex medical speech without custom vocabulary configuration.
Core Features & Capabilities
- Medical Terminology Recognition: Accurate transcription of drug names, diagnoses, symptoms, and procedures.
- Streaming Transcription: Real-time clinical dictation via WebSocket.
- Speaker Diarization: Labels clinician and patient voices separately.
- Smart Formatting: Handles medical number formats, dosages, and dates.
- Entity Detection: Extracts medical entities from audio for downstream processing.
- Custom Vocabulary (keyterm): Add institution-specific or rare drug names to further boost accuracy.
- Dictation Mode: Optimized for voice-driven clinical note-taking workflows.
- Filler Word Detection: Removes hesitation markers common in dictation speech.
Comparison with Other Models
- VS Deepgram Nova-3: Nova-3 Medical is fine-tuned for clinical audio and priced lower per minute; Nova-3 is the general-purpose English model for non-medical use cases.
- VS Deepgram Nova-3 General: Nova-3 Medical is domain-specialized for healthcare; Nova-3 General covers 30+ languages for general multilingual workflows.
- VS AssemblyAI Slam-1: Nova-3 Medical focuses on clinical ASR accuracy; Slam-1 provides semantic understanding and prompt-based customization for enterprise transcription workflows.
Use cases
Clinical documentation: Nova-3 Medical is documented for real-time clinical note-taking and streamlining doctor-patient conversations into structured notes ready for EHR integration.
Prescription workflows: It is documented for capturing prescription instructions by voice, converting unstructured dictation into structured medication orders, and routing them for pharmacy handling.
Appointment scheduling and patient registration: It is documented for voice-driven scheduling, registration, cancellations, and follow-ups in healthcare settings.
Telehealth and clinical decision support: It is described as suited to real-time healthcare applications such as telemedicine, digital health platforms, and clinical decision support systems.
How to use the Nova-3 Medical API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/stt/create' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "deepgram/nova-3-medical"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "deepgram/nova-3-medical"
}
response = requests.post("https://api.aimlapi.com/v1/stt/create", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/stt/create", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "deepgram/nova-3-medical"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v1/stt/create?generation_id=<id> until the status is completed.
Models similar to Nova-3 Medical
Related articles
-1%20(1).webp)
Nova-3 Medical FAQ
What inputs and outputs does Nova-3 Medical support?
Nova-3 Medical takes audio as input and returns text.
When was Nova-3 Medical released?
Nova-3 Medical became available on June 4, 2026.
How much does Nova-3 Medical cost?
Nova-3 Medical is priced at output $0.00009317 / sec.
Who created Nova-3 Medical?
Nova-3 Medical was built by Deepgram.
How do I call Nova-3 Medical on AI/ML API?
Use deepgram/nova-3-medical as the model id on AI/ML API.
Is Nova-3 Medical available through a single API key?
Yes. Nova-3 Medical is served through AI/ML API, so the same key and endpoint format used for other models applies.
Is Nova-3 Medical able to recognize clinical terms and drug names?
Nova-3 Medical is built by Deepgram specifically for medical and healthcare terminology, so it is designed to handle clinical terms and drug names.
What makes Nova-3 Medical different from a general-purpose speech-to-text model?
Deepgram designed Nova-3 Medical as a specialized ASR model focused on medical and healthcare terminology rather than general speech recognition.
What is the Nova-3 Medical model ID?
Use deepgram/nova-3-medical as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.