2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. MAI-Transcribe-2 (preview) leads on raw accuracy; Gemini 3.5 Transcribe is fastest; Gemini 3.5 Transcribe covers the most languages; MAI-Transcribe-2 (preview) is cheapest.
Verdict · who wins what
Most accurate
MAI-Transcribe-2 (preview)
7.8% WER
Microsoft Azure
Fastest
Gemini 3.5 Transcribe
1.0× realtime
Google Gemini
Most languages
Gemini 3.5 Transcribe
72 languages
Google Gemini
Cheapest
MAI-Transcribe-2 (preview)
$0.0017/min
Microsoft Azure
Comparing
2 models · same benchmark
1
MAI-Transcribe-2 (preview)
Microsoft Azure
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.
2
Gemini 3.5 Transcribe
Google Gemini
Google Gemini batch transcription with word timestamps, optional speaker labels and custom vocabulary.
MAI-Transcribe-2 (preview)
field · 36 models
lower-left is better
general
legal
medical
noisy
technical
uk
us
Latency p99
946ms
5.1s
$10.08
$30.24
1,000 hours
$100.80
$302.40
Yes
Auto-detect language
Yes
Yes
Live / streaming
No
No
Custom vocabulary
Yes
Yes
Max file size
250 MB
No limit
Max duration
2 h
30 min
Compliance
—
Is MAI-Transcribe-2 (preview) or Gemini 3.5 Transcribe more accurate?
MAI-Transcribe-2 (preview) is more accurate, with a 7.8% word error rate versus 10.4% for Gemini 3.5 Transcribe, on our standardized benchmark.
Which is cheaper, MAI-Transcribe-2 (preview) or Gemini 3.5 Transcribe?
MAI-Transcribe-2 (preview) is cheaper at $0.0017/min versus $0.0050/min for Gemini 3.5 Transcribe.
Should you choose MAI-Transcribe-2 (preview) or Gemini 3.5 Transcribe?
Choose MAI-Transcribe-2 (preview) for accuracy and lower cost; choose Gemini 3.5 Transcribe for speed and language coverage.