2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Soniox STT (Async) leads on raw accuracy; Google Latest (Long) is fastest; Google Latest (Long) covers the most languages; Soniox STT (Async) is cheapest.
Verdict · who wins what
Most accurate
Soniox STT (Async)
8.7% WER
Soniox
Fastest
Google Latest (Long)
0.4× realtime
Google Cloud
Most languages
Google Latest (Long)
40 languages
Google Cloud
Cheapest
Soniox STT (Async)
$0.0017/min
Soniox
Comparing
2 models · same benchmark
1
Google Latest (Long)
Google Cloud
Conformer model for long-form audio (minutes to hours)
2
Soniox STT (Async)
Soniox
Soniox async batch transcription — one multilingual model across 60+ languages with speaker diarization, per-word timestamps, and automatic language identification, at a low flat token-based rate.
Google Latest (Long)
Soniox STT (Async)
field · 33 models
lower-left is better
general
legal
medical
noisy
technical
uk
us
Latency p99
13.5s
6.2s
$10.08
1,000 hours
$640.80
$100.80
No
Auto-detect language
No
Yes
Live / streaming
No
No
Custom vocabulary
No
No
Max file size
No limit
No limit
Max duration
8 h
5 h
Compliance
—
Is Google Latest (Long) or Soniox STT (Async) more accurate?
Soniox STT (Async) is more accurate, with a 8.7% word error rate versus 22.6% for Google Latest (Long), on our standardized benchmark.
Which is cheaper, Google Latest (Long) or Soniox STT (Async)?
Soniox STT (Async) is cheaper at $0.0017/min versus $0.0107/min for Google Latest (Long).
Should you choose Google Latest (Long) or Soniox STT (Async)?
Choose Google Latest (Long) for speed and language coverage; choose Soniox STT (Async) for accuracy and lower cost.
