Nova-3 overview
Nova-3 by Deepgram
Supports streaming transcription, speaker diarization, smart formatting, and intent/topic detection for monolingual English workflows.
Nova-3 specs
- Model ID
deepgram/nova-3- Developer
- Deepgram
- Input
- Audio
- Output
- Text
- Endpoint
POST https://api.aimlapi.com/v1/stt/create
Deepgram Nova-3 is an advanced speech-to-text model built on Deepgram's end-to-end deep learning architecture. It delivers industry-leading word error rates for English, real-time streaming transcription via WebSocket, and a rich set of audio intelligence features, making it suitable for contact centers, meeting transcription, voice analytics, and developer applications.
Architecture Breakdown
Nova-3 uses Deepgram's proprietary end-to-end deep learning pipeline that processes raw audio directly, eliminating multi-step feature extraction. This reduces error accumulation and enables faster, more accurate inference across diverse recording conditions.
Comparison with Other Models
VS Deepgram Nova-3 General: Nova-3 is optimized for English-only workflows with maximum accuracy, while Nova-3 General adds multilingual support at the same price point.
VS Deepgram Nova-3 Medical: Nova-3 Medical is fine-tuned for clinical terminology and healthcare audio; Nova-3 is the general-purpose English model at a higher per-minute rate.
Use cases
Nova-3 is documented as suited to real-time contact center transcription and automation. It is described as fitting contact center workflows, including real-time transcription and automation with customer support systems.
Nova-3 is documented as suited to meeting transcription and event captioning. The model is listed as recommended for meetings and event captioning, including multi-speaker audio.
Nova-3 is documented as suited to noisy or far-field audio. Deepgram describes it as a strong fit for noisy, multi-speaker, and far-field environments such as drive-thrus and call centers.
Nova-3 is documented as suited to multilingual live applications. Deepgram says it supports real-time multilingual transcription and is suited to global customer support, voice agents, and live captioning.
Capabilities
- Reasoning
- Streaming
How to use the Nova-3 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"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "deepgram/nova-3"
}
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"
}),
});
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
Related articles
-1%20(1).webp)
Nova-3 FAQ
What inputs and outputs does Nova-3 support?
Nova-3 takes audio as input and returns text.
When was Nova-3 released?
Nova-3 became available on June 4, 2026.
How much does Nova-3 cost?
Nova-3 is priced at output $0.0001668 / sec.
Who created Nova-3?
Nova-3 was built by Deepgram.
How do I call Nova-3 on AI/ML API?
Use deepgram/nova-3 as the model id on AI/ML API.
Is Nova-3 available through a single API key?
Yes. Nova-3 is served through AI/ML API, so the same key and endpoint format used for other models applies.
Does Nova-3 support real-time streaming transcription?
Yes, Nova-3 supports streaming as one of its capabilities, alongside reasoning.
What is the Nova-3 model ID?
Use deepgram/nova-3 as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.