About Deepgram Nova 3

Speech-to-text transcription using the Nova-3 model with multi-language support and advanced customizable settings for production workloads.

transcriptionspeech to text

Deepgram Nova 3 specs

Model ID: deepgram-nova-3
Provider: Deepgram
Category: Transcription
Input: audio
Output: text
Endpoints: POST /v1/audio/transcriptions

Deepgram Nova 3 API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

Type

Spec

Rate

Transcription

per minute of audio

$0.014

Compare on the full pricing page

How to call the Deepgram Nova 3 API

Deepgram Nova 3 runs through POST /v1/audio/transcriptions. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Get an API key from the EmpirioLabs dashboard.

cURL: submit the job

curl https://api.empiriolabs.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepgram-nova-3",
    "audio_url": "https://example.com/meeting-recording.mp3"
  }'

cURL: poll for the result

curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY"

Python

import requests

response = requests.post(
    "https://api.empiriolabs.ai/v1/audio/transcriptions",
    headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
    json={
        "model": "deepgram-nova-3",
        "audio_url": "https://example.com/meeting-recording.mp3",
    },
)
job = response.json()

# Generation runs as an async job. Poll until it completes.
import time
while True:
    status = requests.get(
        f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
        headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
    ).json()
    if status.get("status") in ("completed", "failed"):
        print(status)
        break
    time.sleep(5)

Full Deepgram Nova 3 API reference

Deepgram Nova 3 API parameters

Request parameters supported by the Deepgram Nova 3 API on EmpirioLabs. Defaults apply when a field is omitted.

Parameter	Type	Default	Range / values	Description
file	string	-	-	Audio file (mp3, wav, m4a, ogg, etc.) uploaded as multipart/form-data.
file_url	string	-	-	URL of the audio to transcribe. Mutually exclusive with file.
smart_format	boolean	true	-	Apply smart formatting (capitalize, punctuate, format numbers/dates).
profanity_filter	boolean	false	-	Mask profane words in the transcript with ****.
numerals	boolean	false	-	Convert spoken numbers to digits (e.g. "five" → "5").
measurements	boolean	false	-	Convert measurement words to abbreviations (e.g. "kilograms" → "kg").
language	enum	auto	auto, en, es, fr, de, it, pt, ja, zh, hi, ru, nl	ISO 639-1 language code. Auto-detect if omitted.
redact_pii	boolean	false	-	Mask personally-identifiable information in the transcript.
redact_pci	boolean	false	-	Mask payment card numbers in the transcript.
keyterm	string	-	-	Comma-separated key terms to boost recognition accuracy for (jargon, names).
diarize	boolean	false	-	Identify different speakers and tag each utterance with a speaker label.
paragraphs	boolean	true	-	Group output into paragraphs based on pauses and speaker turns.
dictation	boolean	false	-	Interpret commands like "period", "comma", "new line" as punctuation/formatting.
punctuate	boolean	true	-	Add punctuation to the transcript.

2 more parameters in the docs

Good to know

Auto-detected languages

English, Spanish, French, German, Italian, Portuguese, Japanese, Chinese, Hindi, Russian, Dutch.

Custom Key Terms

English only, ≤500 tokens total
Improves recognition of domain-specific vocabulary

Feature interactions

Diarization auto-enables utterances
Smart format and paragraphs auto-enable punctuation
PCI/PII redaction and profanity filter are off by default

Deepgram Nova 3 API: common questions

How much does the Deepgram Nova 3 API cost?

On EmpirioLabs, Deepgram Nova 3 is billed pay as you go: Transcription $0.014 per minute of audio. The live rate card on this page always matches what the API charges.

Which endpoint does Deepgram Nova 3 use?

Deepgram Nova 3 is served through POST /v1/audio/transcriptions on api.empiriolabs.ai with standard bearer-token authentication.

Can I try Deepgram Nova 3 in the browser before integrating?

Yes. The EmpirioLabs playground runs Deepgram Nova 3 in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Deepgram Nova 3 API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.

Deepgram Nova 3 API