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 Voxtral Mini Transcribe

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

Open both in playground

Verdict · who wins what

Most accurate

Voxtral Mini Transcribe

12.7% WER

Mistral (Voxtral)

Fastest

Voxtral Mini Transcribe

0.2× realtime

Mistral (Voxtral)

Most languages

Nova-2

33 languages

Deepgram

Cheapest

Voxtral Mini Transcribe

$0.0030/min

Mistral (Voxtral)

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

Voxtral Mini Transcribe

Mistral (Voxtral)

$0.0030/min
#7 · 80.7

Mistral Voxtral Mini Transcribe — EU-hosted batch transcription with speaker diarization, segment timestamps, and custom vocabulary (context bias). Strong accuracy at very low cost; handles recordings up to 3 hours.

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

76.2

80.7

Accuracy rank

of 35

#18

#7

Word error rate

WER

16.5%

12.7%

Character error rate

CER

11.9%

8.0%

Match error rate

MER

15.4%

11.5%

Word info lost

WIL

21.0%

15.8%

Languages

33

8

Cost vs. accuracy

overall WER vs price

Nova-2

Voxtral Mini Transcribe

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

63.7%
21.0%

conversational

10.2%
10.0%

finance

11.3%
6.8%

Accuracy by accent

WER · English

african

26.2%
27.7%

australian

15.4%
6.2%

indian

25.4%
12.7%

Speed & latency

p50 → p99

Processing speed

× realtime

0.1×

0.2×

Latency p50

1.6s

2.3s

Latency p90

3.7s

2.3s

Realtime / streaming

Streaming benchmark averages

Realtime rank

of 17

#4

—

Realtime score

0–100

78.0

—

Time to first word

986ms

—

Reliability

Rolling 30 days

Uptime

83.33%

100.00%

Error rate

16.67%

0.00%

Pricing

billed per second

Rate

per minute

$0.0058

$0.0030

Billing granularity

per 1s

per 1s

1 hour of audio

$0.35

$0.18

100 hours

$34.92

Capabilities

Feature support

Speaker diarization

Yes

Yes

Word-level timestamps

Yes

No

Code-switching

Yes

Coverage & deployment

Languages · formats · regions

Languages

33

8

Mode

Batch & Realtime

Batch

Region

United States

France

Audio formats

general

13.1%
6.1%

legal

3.8%
3.1%

medical

7.3%
6.3%

noisy

31.3%
47.4%

technical

4.9%
5.6%

uk

11.9%
3.0%

us

9.4%
0.0%

Latency p99

3.7s

2.3s

Final drain

192ms

—

Real-time factor

1.02×

—

Flicker

10.5%

—

Cadence

0.8/s

—

$18.00

1,000 hours

$349.20

$180.00

No

Auto-detect language

Yes

Yes

Live / streaming

Yes

No

Custom vocabulary

Yes

Yes

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

Max file size

2 GB

No limit

Max duration

No limit

15 min

Compliance

HIPAA
SOC2
GDPR
GDPR

Frequently asked questions

Is Nova-2 or Voxtral Mini Transcribe more accurate?

Voxtral Mini Transcribe is more accurate, with a 12.7% word error rate versus 16.5% for Nova-2, on our standardized benchmark.

Which is cheaper, Nova-2 or Voxtral Mini Transcribe?

Voxtral Mini Transcribe is cheaper at $0.0030/min versus $0.0058/min for Nova-2.

Should you choose Nova-2 or Voxtral Mini Transcribe?

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