Nova-3 General API

Q: What is the Nova-3 General model ID?

Use deepgram/nova-3-general as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.

Try this model

Nova-3: Deepgram next-generation ASR model with improved accuracy and multilingual support.

Modalities: AudioText
Model type: Speech to text
Released: Jun 4, 2026

Nova-3 General overview

Nova-3 General by Deepgram

Supports streaming and batch transcription, automatic language detection, speaker diarization, and advanced audio intelligence for multilingual workflows.

Nova-3 General specs

Model ID: deepgram/nova-3-general
Developer: Deepgram
Input: Audio
Output: Text
Endpoint: POST https://api.aimlapi.com/v1/stt/create

Deepgram Nova-3 General extends the Nova-3 architecture with multilingual capabilities, supporting 30+ languages with automatic language detection. It is designed for global voice applications, multilingual contact centers, international content pipelines, and cross-language analytics, all without requiring pre-specification of the input language.

Performance Benchmarks

Supports 30+ languages with competitive per-language word error rates.
Automatic language detection runs in parallel with transcription.
Sub-second latency in streaming mode.
Handles code-switching in select language pairs.
Consistent accuracy across diverse accents and recording conditions.

Architecture Breakdown

Nova-3 General shares the same end-to-end deep learning foundation as Nova-3, extended with a multilingual language head trained on diverse language corpora. Language identification is embedded in the transcription pipeline, removing the need for a separate detection step.

Core Features & Capabilities

Multilingual Streaming: Real-time transcription across 30+ languages via WebSocket.
Auto Language Detection: Dynamically identifies spoken language, no pre-configuration needed.
Speaker Diarization: Labels individual speakers across multilingual audio sessions.
Smart Formatting: Locale-aware number, date, and punctuation formatting.
Intent & Topic Detection: Custom and model-detected intents and topics across languages.
Entity Detection: Extracts key entities from multilingual audio content.
Custom Vocabulary (keyterm): Add domain-specific terms per language to improve accuracy.
Utterance Segmentation: Segments multilingual streams into labeled speech units.

Comparison with Other Models

VS Deepgram Nova-3: Nova-3 General adds multilingual support at the same price; Nova-3 offers maximum accuracy for English-only use cases.
VS Deepgram Nova-3 Medical: Nova-3 General is the general-purpose multilingual model; Nova-3 Medical is specialized for healthcare audio at a lower price per minute.

Use cases

Meeting transcription is a documented fit for Nova-3 General, which Deepgram describes as recommended for meetings and as meeting transcription in its Nova-3 use-case guidance.

Event captioning is another documented use case; Deepgram’s models overview says Nova-3 is recommended for event captioning, and its comparison page lists event captioning as a Nova-3 use case.

Multi-speaker audio is a stated fit for Nova-3 General, with Deepgram describing it as recommended for multi-speaker audio and for distant, noisy, and overlapping speech conditions.

Multilingual audio is also explicitly documented, with Deepgram recommending Nova-3 for multilingual use and real-time multilingual transcription across multiple languages.

How to use the Nova-3 General API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export 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-general"
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepgram/nova-3-general"
}

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-general"
  }),
});

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.

All posts

The Most Accurate Speech Models: Pick the Right One
AI News
MiniMax Audio: Voices from China
AI NewsDecember 25, 2024
MAI-Voice-2, MAI-Transcribe 1.5 & MAI-Image 2.5 Guide
AI News

Nova-3 General FAQ

What inputs and outputs does Nova-3 General support?

Nova-3 General takes audio as input and returns text.

When was Nova-3 General released?

Nova-3 General became available on June 4, 2026.

How much does Nova-3 General cost?

Nova-3 General is priced at output $0.0001668 / sec.

Who created Nova-3 General?

Nova-3 General was built by Deepgram.

How do I call Nova-3 General on AI/ML API?

Use deepgram/nova-3-general as the model id on AI/ML API.

Is Nova-3 General available through a single API key?

Yes. Nova-3 General is served through AI/ML API, so the same key and endpoint format used for other models applies.

What is Nova-3 General best suited for?

It is Deepgram's next-generation speech-to-text model built for improved transcription accuracy and multilingual support.

Does Nova-3 General handle multiple languages?

Yes, Nova-3 General includes multilingual support as part of its speech-to-text capabilities.

What is the Nova-3 General model ID?

Use deepgram/nova-3-general as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.

Start building with Nova-3 General

Get API key