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 Speechmatics Enhanced

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

Open both in playground

Verdict · who wins what

Most accurate

Speechmatics Enhanced

12.3% WER

Speechmatics

Fastest

Speechmatics Enhanced

0.3× realtime

Speechmatics

Most languages

Speechmatics Enhanced

48 languages

Speechmatics

Cheapest

Nova-3

$0.0077/min

Deepgram

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

Speechmatics Enhanced

Speechmatics

$0.0083/min
#6 · 47.3

Highest accuracy model — 55+ languages, best-in-class

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

71.1

47.3

Accuracy rank

of 35

#29

#6

Word error rate

WER

21.0%

12.3%

Character error rate

CER

11.5%

8.0%

Match error rate

MER

20.0%

11.3%

Word info lost

WIL

25.8%

16.2%

Languages

47

48

Cost vs. accuracy

overall WER vs price

Speechmatics Enhanced

Nova-3

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

63.0%
39.2%

conversational

12.2%
6.4%

finance

9.5%
6.8%

general

23.4%
7.2%

legal

3.8%
2.2%

medical

9.5%
5.7%

noisy

21.8%
40.8%

technical

2.8%
5.3%

Accuracy by accent

WER · English

african

26.2%
7.7%

australian

15.4%
7.7%

indian

27.0%
9.5%

uk

6.0%
3.0%

us

11.3%
1.9%

Speed & latency

p50 → p99

Processing speed

× realtime

0.1×

0.3×

Latency p50

1.3s

8.7s

Latency p90

1.8s

12.1s

Latency p99

1.8s

12.1s

Realtime / streaming

Streaming benchmark averages

Realtime rank

of 17

#3

—

Realtime score

0–100

78.2

—

Time to first word

973ms

—

Final drain

181ms

—

Real-time factor

1.01×

—

Flicker

9.6%

—

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

$0.0077

$0.0083

Billing granularity

per 1s

per 1s

1 hour of audio

$0.46

$0.50

100 hours

$46.08

$49.68

1,000 hours

$460.80

$496.80

Capabilities

Feature support

Speaker diarization

Yes

Yes

Word-level timestamps

Yes

Yes

Code-switching

Yes

Yes

Auto-detect language

Yes

Yes

Live / streaming

Yes

No

Custom vocabulary

Yes

Yes

Coverage & deployment

Languages · formats · regions

Languages

47

48

Mode

Batch & Realtime

Batch

Region

United States

Europe

Audio formats

mp3
wav
flac
m4a
ogg
webm
mp3
wav
flac
m4a
ogg

Max file size

2 GB

1 GB

Max duration

No limit

No limit

Compliance

HIPAA
SOC2
GDPR
SOC2
GDPR

Frequently asked questions

Is Nova-3 or Speechmatics Enhanced more accurate?

Speechmatics Enhanced is more accurate, with a 12.3% word error rate versus 21.0% for Nova-3, on our standardized benchmark.

Which is cheaper, Nova-3 or Speechmatics Enhanced?

Nova-3 is cheaper at $0.0077/min versus $0.0083/min for Speechmatics Enhanced.

Should you choose Nova-3 or Speechmatics Enhanced?

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