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

Whisper Large V3 Turbo vs Scribe v2

2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Scribe v2 leads on raw accuracy; Whisper Large V3 Turbo is fastest; Scribe v2 covers the most languages; Whisper Large V3 Turbo is cheapest.

Open both in playground

Verdict · who wins what

Most accurate

Scribe v2

9.2% WER

ElevenLabs

Fastest

Whisper Large V3 Turbo

1.0× realtime

Cloudflare

Most languages

Scribe v2

76 languages

ElevenLabs

Cheapest

Whisper Large V3 Turbo

$0.0005/min

Cloudflare

Comparing

2 models · same benchmark

1

Batch

Whisper Large V3 Turbo

Cloudflare

$0.0005/min
#10 · 76.7

OpenAI Whisper large-v3-turbo hosted by Cloudflare Workers AI, with word-level timestamps and automatic language detection.

Use This ModelDetails →

2

Batch

Scribe v2

ElevenLabs

$0.0040/min
#3 · 78.2

State-of-the-art batch STT — 90+ languages, speaker diarization, audio tagging

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

76.7

78.2

Accuracy rank

of 38

#10

#3

Word error rate

WER

12.9%

9.2%

Character error rate

CER

9.2%

7.2%

Match error rate

MER

11.9%

8.5%

Word info lost

WIL

16.3%

12.3%

Languages

12

76

Cost vs. accuracy

overall WER vs price

Scribe v2

Whisper Large V3 Turbo

field · 36 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

23.2%
14.6%

conversational

10.0%
7.6%

finance

6.7%
7.6%

general

10.7%
5.4%

legal

2.8%
2.8%

medical

2.1%
5.8%

noisy

36.3%
33.8%

technical

5.2%
3.1%

Accuracy by accent

WER · English

african

24.6%
21.5%

australian

36.9%
3.1%

indian

23.8%
9.5%

uk

6.0%
0.0%

us

9.4%
0.0%

Speed & latency

p50 → p99

Processing speed

× realtime

1.0×

0.2×

Latency p50

5.3s

3.4s

Latency p90

5.3s

4.0s

Latency p99

5.3s

4.0s

Realtime / streaming

Streaming benchmark averages

Realtime rank

—

—

Realtime score

0–100

—

—

Time to first word

—

—

Final drain

—

—

Real-time factor

—

—

Flicker

—

—

Cadence

—

—

Reliability

Rolling 30 days

Uptime

100.00%

100.00%

Error rate

0.00%

0.00%

Pricing

billed per second

Rate

per minute

$0.0005

$0.0040

Billing granularity

per 1s

per 1s

1 hour of audio

$0.03

$0.24

100 hours

$3.24

$24.12

1,000 hours

$32.40

$241.20

Capabilities

Feature support

Speaker diarization

No

Yes

Word-level timestamps

Yes

Yes

Code-switching

No

Yes

Auto-detect language

Yes

Yes

Live / streaming

No

No

Custom vocabulary

No

No

Coverage & deployment

Languages · formats · regions

Languages

12

76

Mode

Batch

Batch

Region

Global

United States

Audio formats

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

Max file size

25 MB

3 GB

Max duration

No limit

10 h

Compliance

—

SOC2
GDPR

Frequently asked questions

Is Whisper Large V3 Turbo or Scribe v2 more accurate?

Scribe v2 is more accurate, with a 9.2% word error rate versus 12.9% for Whisper Large V3 Turbo, on our standardized benchmark.

Which is cheaper, Whisper Large V3 Turbo or Scribe v2?

Whisper Large V3 Turbo is cheaper at $0.0005/min versus $0.0040/min for Scribe v2.

Should you choose Whisper Large V3 Turbo or Scribe v2?

Choose Whisper Large V3 Turbo for speed and lower cost; choose Scribe v2 for accuracy and language coverage.