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 Whisper Large V3

2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Nova-2 leads on raw accuracy; Whisper Large V3 is fastest; Whisper Large V3 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

Whisper Large V3

0.3× realtime

OpenAI

Most languages

Whisper Large V3

98 languages

OpenAI

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

Whisper Large V3

OpenAI

$0.0060/min
#24 · 69.3

OpenAI's Whisper large-v3 model

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

76.2

69.3

Accuracy rank

of 35

#18

#24

Word error rate

WER

16.5%

17.7%

Character error rate

CER

11.9%

13.1%

Match error rate

MER

15.4%

16.6%

Word info lost

WIL

21.0%

21.6%

Languages

33

98

Cost vs. accuracy

overall WER vs price

Nova-2

Whisper Large V3

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

63.7%
62.7%

conversational

10.2%
11.2%

finance

11.3%
6.0%

general

13.1%
14.9%

legal

3.8%
2.4%

medical

7.3%
6.6%

noisy

31.3%
36.3%

technical

4.9%
6.5%

Accuracy by accent

WER · English

african

26.2%
24.6%

australian

15.4%
15.4%

indian

25.4%
19.1%

uk

11.9%
3.0%

us

9.4%
3.8%

Speed & latency

p50 → p99

Processing speed

× realtime

0.1×

0.3×

Latency p50

1.6s

3.5s

Latency p90

3.7s

4.3s

Latency p99

3.7s

4.3s

Realtime / streaming

Streaming benchmark averages

Realtime rank

of 17

#4

—

Realtime score

0–100

78.0

—

Time to first word

986ms

—

Final drain

192ms

—

Real-time factor

1.02×

—

Flicker

10.5%

—

Cadence

0.8/s

—

Reliability

Rolling 30 days

Uptime

50.00%

100.00%

Error rate

50.00%

0.00%

Pricing

billed per second

Rate

per minute

$0.0058

$0.0060

Billing granularity

per 1s

per 1s

1 hour of audio

$0.35

$0.36

100 hours

$34.92

$36.00

1,000 hours

$349.20

$360.00

Capabilities

Feature support

Speaker diarization

Yes

No

Word-level timestamps

Yes

Yes

Code-switching

Yes

No

Auto-detect language

Yes

Yes

Live / streaming

Yes

No

Custom vocabulary

Yes

No

Coverage & deployment

Languages · formats · regions

Languages

33

98

Mode

Batch & Realtime

Batch

Region

United States

United States

Audio formats

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

Max file size

2 GB

25 MB

Max duration

No limit

No limit

Compliance

HIPAA
SOC2
GDPR
SOC2
GDPR

Frequently asked questions

Is Nova-2 or Whisper Large V3 more accurate?

Nova-2 is more accurate, with a 16.5% word error rate versus 17.7% for Whisper Large V3, on our standardized benchmark.

Which is cheaper, Nova-2 or Whisper Large V3?

Nova-2 is cheaper at $0.0058/min versus $0.0060/min for Whisper Large V3.

Should you choose Nova-2 or Whisper Large V3?

Choose Nova-2 for accuracy and lower cost; choose Whisper Large V3 for speed and language coverage.