2 models compared on the same benchmark — accuracy, latency, price, language coverage and capabilities. Soniox STT (Async) leads on raw accuracy; Soniox STT (Async) is cheapest.
Verdict · who wins what
Most accurate
Soniox STT (Async)
8.7% WER
Soniox
Fastest
—
—
Most languages
—
—
Cheapest
Soniox STT (Async)
$0.0017/min
Soniox
Comparing
2 models · same benchmark
1
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.
2
Soniox STT Realtime
Soniox
Soniox realtime streaming transcription — low-latency multilingual STT across 60+ languages with speaker diarization, per-word timestamps, and automatic language identification over a single WebSocket.
general
—
legal
—
medical
—
noisy
—
technical
—
uk
—
us
—
6.2s
—
Final drain
—
0ms
Real-time factor
—
1.09×
Flicker
—
66.5%
Cadence
—
3.6/s
$10.08
$11.88
1,000 hours
$100.80
$118.80
No
Auto-detect language
Yes
Yes
Live / streaming
No
Yes
Custom vocabulary
No
No
Max file size
No limit
No limit
Max duration
5 h
5 h
Compliance
—
—
Is Soniox STT (Async) or Soniox STT Realtime more accurate?
Soniox STT (Async) has a published benchmark at 8.7% word error rate. Soniox STT Realtime has not been benchmarked yet.
Which is cheaper, Soniox STT (Async) or Soniox STT Realtime?
Soniox STT (Async) is cheaper at $0.0017/min versus $0.0020/min for Soniox STT Realtime.
Should you choose Soniox STT (Async) or Soniox STT Realtime?
Soniox STT (Async) is the stronger choice overall, leading on accuracy and lower cost.
