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 fastest; Scribe v2 Realtime covers the most languages; Soniox STT (Async) is cheapest.
Verdict · who wins what
Most accurate
Soniox STT (Async)
8.7% WER
Soniox
Fastest
Soniox STT (Async)
0.1× realtime
Soniox
Most languages
Scribe v2 Realtime
76 languages
ElevenLabs
Cheapest
Soniox STT (Async)
$0.0017/min
Soniox
Comparing
2 models · same benchmark
1
Scribe v2 Realtime
ElevenLabs
Most accurate low-latency STT — <150ms, 90+ languages
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.
general
—
legal
—
medical
—
noisy
—
technical
—
uk
—
us
—
—
6.2s
Final drain
302ms
—
Real-time factor
1.09×
—
Flicker
57.9%
—
Cadence
1.0/s
—
$10.08
1,000 hours
$388.80
$100.80
No
Auto-detect language
Yes
Yes
Live / streaming
Yes
No
Custom vocabulary
No
No
Max file size
3 GB
No limit
Max duration
10 h
5 h
Compliance
—
Is Scribe v2 Realtime or Soniox STT (Async) more accurate?
Soniox STT (Async) has a published benchmark at 8.7% word error rate. Scribe v2 Realtime has not been benchmarked yet.
Which is cheaper, Scribe v2 Realtime or Soniox STT (Async)?
Soniox STT (Async) is cheaper at $0.0017/min versus $0.0065/min for Scribe v2 Realtime.
Should you choose Scribe v2 Realtime or Soniox STT (Async)?
Choose Scribe v2 Realtime for language coverage; choose Soniox STT (Async) for accuracy, speed, and lower cost.
