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

MAI-Transcribe-2 (preview) vs Chirp 3

2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. MAI-Transcribe-2 (preview) leads on raw accuracy; Chirp 3 is fastest; Chirp 3 covers the most languages; MAI-Transcribe-2 (preview) is cheapest for batch audio.

Open both in playground

Verdict · who wins what

Most accurate

MAI-Transcribe-2 (preview)

7.8% WER

Microsoft Azure

Fastest

Chirp 3

0.3× realtime

Google Cloud

Most languages

Chirp 3

68 languages

Google Cloud

Cheapest

MAI-Transcribe-2 (preview)

$0.0017/min · Batch rate

Microsoft Azure

Comparing

2 models · same benchmark

1

Batch

MAI-Transcribe-2 (preview)

Microsoft Azure

$0.0017/min
#1 · 89.9

Batch rate

Microsoft MAI-Transcribe-2 — Microsoft AI's in-house transcription model, in public preview on Azure Speech. 60 languages with automatic language detection and mid-sentence code-switching, speaker diarization, word-level timestamps and custom vocabulary. Accepts WAV, MP3 and FLAC.

Use This ModelDetails →

2

Batch

Chirp 3

Google Cloud

$0.0107/min
#6 · 45.0

Batch rate

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

Use This ModelDetails →

Overview

30-day benchmark average

Overall score

0–100

89.9

45.0

Accuracy rank

of 40

#1

#6

Word error rate

WER

7.8%

10.0%

Character error rate

CER

6.1%

5.8%

Match error rate

MER

7.0%

9.7%

Word info lost

WIL

10.2%

14.1%

Languages

59

68

Cost vs. accuracy

overall WER vs price

Chirp 3

MAI-Transcribe-2 (preview)

field · 38 models

lower-left is better

Accuracy by category

WER · lower is better

code_switching

16.4%
17.1%

conversational

5.2%
4.7%

finance

7.1%
7.1%

general

5.1%
8.2%

legal

2.9%
2.9%

medical

2.1%
1.9%

noisy

26.3%
29.2%

technical

1.1%
3.7%

Accuracy by accent

WER · English

african

24.6%
20.0%

australian

3.1%
16.9%

indian

9.5%
27.0%

uk

1.5%
3.0%

us

5.7%
5.7%

Speed & latency

p50 → p99

Processing speed

× realtime

—

0.3×

Latency p50

912ms

11.0s

Latency p90

946ms

11.2s

Latency p99

946ms

11.2s

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

93.33%

75.00%

Error rate

6.67%

25.00%

Pricing

billed per second

Rate

per minute · Batch

$0.0017

$0.0107

Billing granularity

per 1s

per 15s

1 hour of audio

Batch

$0.10

$0.64

100 hours

Batch

$10.08

$64.08

1,000 hours

Batch

$100.80

$640.80

Capabilities

Feature support

Speaker diarization

Yes

Yes

Word-level timestamps

Yes

No

Code-switching

Yes

Yes

Auto-detect language

Yes

Yes

Live / streaming

No

No

Custom vocabulary

Yes

Yes

Coverage & deployment

Languages · formats · regions

Languages

59

68

Mode

Batch

Batch

Region

United States

United States

Audio formats

wav
mp3
flac
mp3
wav
flac
ogg
webm
amr

Max file size

250 MB

No limit

Max duration

2 h

8 h

Compliance

HIPAA
SOC2
GDPR
HIPAA
SOC2
GDPR

Frequently asked questions

Is MAI-Transcribe-2 (preview) or Chirp 3 more accurate?

MAI-Transcribe-2 (preview) is more accurate, with a 7.8% word error rate versus 10.0% for Chirp 3, on our standardized benchmark.

Which is cheaper, MAI-Transcribe-2 (preview) or Chirp 3?

For batch audio, MAI-Transcribe-2 (preview) is cheaper at $0.0017/min versus $0.0107/min for Chirp 3.

Should you choose MAI-Transcribe-2 (preview) or Chirp 3?

Choose MAI-Transcribe-2 (preview) for accuracy and lower cost; choose Chirp 3 for speed and language coverage.