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

Chirp 3 vs GPT-4o Transcribe Diarize

2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Chirp 3 leads on raw accuracy; Chirp 3 is fastest; Chirp 3 covers the most languages; GPT-4o Transcribe Diarize is cheapest.

Open both in playground

Verdict · who wins what

Most accurate

Chirp 3

10.0% WER

Google Cloud

Fastest

Chirp 3

0.3× realtime

Google Cloud

Most languages

Chirp 3

68 languages

Google Cloud

Cheapest

GPT-4o Transcribe Diarize

$0.0060/min

OpenAI

Comparing

2 models · same benchmark

1

Batch

Chirp 3

Google Cloud

$0.0107/min
#4 · 45.0

Google's latest generative ASR foundation model — 85+ languages

Use This ModelDetails →

2

Batch

GPT-4o Transcribe Diarize

OpenAI

$0.0060/min
#12 · 50.7

GPT-4o transcription with built-in speaker diarization

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

45.0

50.7

Accuracy rank

of 35

#4

#12

Word error rate

WER

10.0%

14.6%

Character error rate

CER

5.8%

10.0%

Match error rate

MER

9.7%

13.5%

Word info lost

WIL

14.1%

19.9%

Languages

68

12

Cost vs. accuracy

overall WER vs price

Chirp 3

GPT-4o Transcribe Diarize

field · 33 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

17.1%
25.5%

conversational

4.7%
12.2%

finance

7.1%
6.3%

general

8.2%
14.5%

legal

2.9%
2.3%

medical

1.9%
1.9%

noisy

29.2%
32.5%

technical

3.7%
4.6%

Accuracy by accent

WER · English

african

20.0%
27.7%

australian

16.9%
29.2%

indian

27.0%
36.5%

uk

3.0%
13.4%

us

5.7%
18.9%

Speed & latency

p50 → p99

Processing speed

× realtime

0.3×

0.2×

Latency p50

11.0s

17.2s

Latency p90

11.2s

18.1s

Latency p99

11.2s

18.1s

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

69.23%

100.00%

Error rate

30.77%

0.00%

Pricing

billed per second

Rate

per minute

$0.0107

$0.0060

Billing granularity

per 15s

per 1s

1 hour of audio

$0.64

$0.36

100 hours

$64.08

$36.00

1,000 hours

$640.80

$360.00

Capabilities

Feature support

Speaker diarization

Yes

Yes

Word-level timestamps

No

No

Code-switching

Yes

No

Auto-detect language

Yes

Yes

Live / streaming

No

No

Custom vocabulary

Yes

No

Coverage & deployment

Languages · formats · regions

Languages

68

12

Mode

Batch

Batch

Region

United States

United States

Audio formats

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

Max file size

No limit

25 MB

Max duration

8 h

No limit

Compliance

HIPAA
SOC2
GDPR
SOC2
GDPR

Frequently asked questions

Is Chirp 3 or GPT-4o Transcribe Diarize more accurate?

Chirp 3 is more accurate, with a 10.0% word error rate versus 14.6% for GPT-4o Transcribe Diarize, on our standardized benchmark.

Which is cheaper, Chirp 3 or GPT-4o Transcribe Diarize?

GPT-4o Transcribe Diarize is cheaper at $0.0060/min versus $0.0107/min for Chirp 3.

Should you choose Chirp 3 or GPT-4o Transcribe Diarize?

Choose Chirp 3 for accuracy, speed, and language coverage; choose GPT-4o Transcribe Diarize for lower cost.