LLM Reference

Deepgram Nova-3 on Deepgram API

Deepgram Nova · Deepgram

Serverless

Last refreshed 2026-06-07. Next refresh: weekly.

Why use Deepgram Nova-3 on Deepgram API?

Deepgram API offers Deepgram Nova-3 with pay-as-you-go pricing at $0.005/minute. Deepgram's API provides hosted speech-to-text, text-to-speech, and voice-agent audio models, including Nova, Flux, and Aura model families.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: nova-3
Model ID
nova-3

Request example

Curated snippets for this provider are not sourced yet. Use Deepgram API documentation with model ID nova-3.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Capabilities

MultimodalAudio

About Deepgram Nova-3

Nova-3 is Deepgram's current-generation speech-to-text model, released February 12, 2025. Achieves 6.84% median WER streaming and 5.26% batch — a ~54% improvement over competitors. Supports real-time multilingual transcription across 31 languages with self-serve keyterm prompting (up to 100 terms) and real-time redaction (up to 50 entity types). Also includes nova-3-medical specialization. Streaming: $0.0048/min (mono), $0.0058/min (multilingual); pre-recorded: $0.0077/min (mono). API ID: nova-3.

FAQ

What API model ID do I use for Deepgram Nova-3 on Deepgram API?

Use the model ID nova-3 when calling Deepgram API's API.

Who created Deepgram Nova-3?

Deepgram Nova-3 was created by Deepgram as part of the Deepgram Nova model family.

Is Deepgram Nova-3 open source?

Deepgram Nova-3 is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2025-02-12
Architectureneural

Related Models on Deepgram API