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-3 vs Whisper Large V3

2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Whisper Large V3 leads on raw accuracy; Nova-3 is fastest; Nova-3 covers the most languages; Whisper Large V3 is cheapest.

Open both in playground

Verdict · who wins what

Most accurate

Whisper Large V3

14.4% WER

Groq

Fastest

Nova-3

0.1× realtime

Deepgram

Most languages

Nova-3

47 languages

Deepgram

Cheapest

Whisper Large V3

$0.0019/min

Groq

Comparing

2 models · same benchmark

1

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 →

2

Batch

Whisper Large V3

Groq

$0.0019/min
#11 · 79.9

OpenAI Whisper large-v3 served on Groq's LPU hardware — top Whisper accuracy at Groq speed and cost, with word-level timestamps and automatic language detection.

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

71.1

79.9

Accuracy rank

of 35

#29

#11

Word error rate

WER

21.0%

14.4%

Character error rate

CER

11.5%

11.2%

Match error rate

MER

20.0%

13.3%

Word info lost

WIL

25.8%

18.2%

Languages

47

12

Cost vs. accuracy

overall WER vs price

Nova-3

Whisper Large V3

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

63.0%
68.5%

conversational

12.2%
10.9%

finance

9.5%
6.4%

Accuracy by accent

WER · English

african

26.2%
26.2%

australian

15.4%
12.3%

indian

27.0%
19.1%

Speed & latency

p50 → p99

Processing speed

× realtime

0.1×

0.0×

Latency p50

1.3s

3.1s

Latency p90

1.8s

3.6s

Realtime / streaming

Streaming benchmark averages

Realtime rank

of 17

#3

—

Realtime score

0–100

78.2

—

Time to first word

973ms

—

Reliability

Rolling 30 days

Uptime

100.00%

—

Error rate

0.00%

—

Pricing

billed per second

Rate

per minute

$0.0077

$0.0019

Billing granularity

per 1s

per 1s

1 hour of audio

$0.46

$0.11

100 hours

$46.08

Capabilities

Feature support

Speaker diarization

Yes

No

Word-level timestamps

Yes

Yes

Code-switching

Yes

Coverage & deployment

Languages · formats · regions

Languages

47

12

Mode

Batch & Realtime

Batch

Region

United States

United States

Audio formats

general

23.4%
8.1%

legal

3.8%
2.7%

medical

9.5%
2.8%

noisy

21.8%
36.3%

technical

2.8%
5.3%

uk

6.0%
6.0%

us

11.3%
5.7%

Latency p99

1.8s

3.6s

Final drain

181ms

—

Real-time factor

1.01×

—

Flicker

9.6%

—

Cadence

0.8/s

—

$11.16

1,000 hours

$460.80

$111.60

No

Auto-detect language

Yes

Yes

Live / streaming

Yes

No

Custom vocabulary

Yes

No

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

Max file size

2 GB

100 MB

Max duration

No limit

No limit

Compliance

HIPAA
SOC2
GDPR

—

Frequently asked questions

Is Nova-3 or Whisper Large V3 more accurate?

Whisper Large V3 is more accurate, with a 14.4% word error rate versus 21.0% for Nova-3, on our standardized benchmark.

Which is cheaper, Nova-3 or Whisper Large V3?

Whisper Large V3 is cheaper at $0.0019/min versus $0.0077/min for Nova-3.

Should you choose Nova-3 or Whisper Large V3?

Choose Nova-3 for speed and language coverage; choose Whisper Large V3 for accuracy and lower cost.