OpenTranscription
OpenTranscription
RankerModelsPlayground
OpenTranscription
OpenTranscription

One API to every speech-to-text model worth using. Compare them on your audio, route to the best one, pay per second.

Platform status

Product

RankerModelsTranscriptionsPlaygroundBlog

Developers

DocumentationReliabilityAPI VersioningStatus

Legal

Privacy PolicyTerms of ServiceSupport
© 2026 OpenTranscription
Back to Models

Nova-2 vs Nova-3

2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Nova-2 leads on raw accuracy; Nova-2 is fastest; Nova-3 covers the most languages; Nova-2 is cheapest.

Open both in playground

Verdict · who wins what

Most accurate

Nova-2

16.5% WER

Deepgram

Fastest

Nova-2

0.1× realtime

Deepgram

Most languages

Nova-3

47 languages

Deepgram

Cheapest

Nova-2

$0.0058/min

Deepgram

Comparing

2 models · same benchmark

1

Batch & Realtime

Nova-2

Deepgram

$0.0058/min
#18 · 76.2

Deepgram's Nova-2 speech recognition

Use This ModelDetails →

2

Batch & Realtime

Nova-3

Deepgram

$0.0077/min
#29 · 71.1

Deepgram's flagship model — 53% lower WER vs competitors, code-switching support

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

76.2

71.1

Accuracy rank

of 35

#18

#29

Word error rate

WER

16.5%

21.0%

Character error rate

CER

11.9%

11.5%

Match error rate

MER

15.4%

20.0%

Word info lost

WIL

21.0%

25.8%

Languages

33

47

Cost vs. accuracy

overall WER vs price

Nova-2

Nova-3

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

63.7%
63.0%

conversational

10.2%
12.2%

finance

11.3%
9.5%

Accuracy by accent

WER · English

african

26.2%
26.2%

australian

15.4%
15.4%

indian

25.4%

Speed & latency

p50 → p99

Processing speed

× realtime

0.1×

0.1×

Latency p50

1.6s

1.3s

Latency p90

3.7s

1.8s

Realtime / streaming

Streaming benchmark averages

Realtime rank

of 17

#4

#3

Realtime score

0–100

78.0

78.2

Time to first word

986ms

973ms

Reliability

Rolling 30 days

Uptime

83.33%

100.00%

Error rate

16.67%

0.00%

Pricing

billed per second

Rate

per minute

$0.0058

$0.0077

Billing granularity

per 1s

per 1s

1 hour of audio

$0.35

$0.46

100 hours

Capabilities

Feature support

Speaker diarization

Yes

Yes

Word-level timestamps

Yes

Yes

Code-switching

Yes

Coverage & deployment

Languages · formats · regions

Languages

33

47

Mode

Batch & Realtime

Batch & Realtime

Region

United States

United States

Audio formats

general

13.1%
23.4%

legal

3.8%
3.8%

medical

7.3%
9.5%

noisy

31.3%
21.8%

technical

4.9%
2.8%
27.0%

uk

11.9%
6.0%

us

9.4%
11.3%

Latency p99

3.7s

1.8s

Final drain

192ms

181ms

Real-time factor

1.02×

1.01×

Flicker

10.5%

9.6%

Cadence

0.8/s

0.8/s

$34.92

$46.08

1,000 hours

$349.20

$460.80

Yes

Auto-detect language

Yes

Yes

Live / streaming

Yes

Yes

Custom vocabulary

Yes

Yes

mp3
wav
flac
m4a
ogg
webm
mp3
wav
flac
m4a
ogg
webm

Max file size

2 GB

2 GB

Max duration

No limit

No limit

Compliance

HIPAA
SOC2
GDPR
HIPAA
SOC2
GDPR

Frequently asked questions

Is Nova-2 or Nova-3 more accurate?

Nova-2 is more accurate, with a 16.5% word error rate versus 21.0% for Nova-3, on our standardized benchmark.

Which is cheaper, Nova-2 or Nova-3?

Nova-2 is cheaper at $0.0058/min versus $0.0077/min for Nova-3.

Should you choose Nova-2 or Nova-3?

Choose Nova-2 for accuracy, speed, and lower cost; choose Nova-3 for language coverage.