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

Amazon Transcribe vs Nova-3

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

Open both in playground

Verdict · who wins what

Most accurate

Amazon Transcribe

13.0% WER

Amazon Web Services

Fastest

Amazon Transcribe

0.4× realtime

Amazon Web Services

Most languages

Amazon Transcribe

77 languages

Amazon Web Services

Cheapest

Amazon Transcribe

$0.0060/min

Amazon Web Services

Comparing

2 models · same benchmark

1

Batch

Amazon Transcribe

Amazon Web Services

$0.0060/min
#8 · 51.5

AWS foundation model-powered ASR — 100+ languages

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

51.5

71.1

Accuracy rank

of 35

#8

#29

Word error rate

WER

13.0%

21.0%

Character error rate

CER

9.2%

11.5%

Match error rate

MER

12.1%

20.0%

Word info lost

WIL

16.7%

25.8%

Languages

77

47

Cost vs. accuracy

overall WER vs price

Nova-3

Amazon Transcribe

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

55.8%
63.0%

conversational

6.9%
12.2%

finance

6.3%
9.5%

general

6.6%
23.4%

legal

6.2%
3.8%

medical

3.7%
9.5%

noisy

41.7%
21.8%

technical

3.2%
2.8%

Accuracy by accent

WER · English

african

24.6%
26.2%

australian

6.2%
15.4%

indian

3.2%
27.0%

uk

0.0%
6.0%

us

1.9%
11.3%

Speed & latency

p50 → p99

Processing speed

× realtime

0.4×

0.1×

Latency p50

12.4s

1.3s

Latency p90

13.0s

1.8s

Latency p99

13.0s

1.8s

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

100.00%

50.00%

Error rate

0.00%

50.00%

Pricing

billed per second

Rate

per minute

$0.0060

$0.0077

Billing granularity

per 1s

per 1s

1 hour of audio

$0.36

$0.46

100 hours

$36.00

$46.08

1,000 hours

$360.00

$460.80

Capabilities

Feature support

Speaker diarization

Yes

Yes

Word-level timestamps

Yes

Yes

Code-switching

Yes

Yes

Auto-detect language

Yes

Yes

Live / streaming

No

Yes

Custom vocabulary

No

Yes

Coverage & deployment

Languages · formats · regions

Languages

77

47

Mode

Batch

Batch & Realtime

Region

United States

United States

Audio formats

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

Max file size

2 GB

2 GB

Max duration

8 h

No limit

Compliance

HIPAA
SOC2
GDPR
HIPAA
SOC2
GDPR

Frequently asked questions

Is Amazon Transcribe or Nova-3 more accurate?

Amazon Transcribe is more accurate, with a 13.0% word error rate versus 21.0% for Nova-3, on our standardized benchmark.

Which is cheaper, Amazon Transcribe or Nova-3?

Amazon Transcribe is cheaper at $0.0060/min versus $0.0077/min for Nova-3.

Should you choose Amazon Transcribe or Nova-3?

Amazon Transcribe is the stronger choice overall, leading on accuracy, speed, lower cost, and language coverage.