← Speech-to-Text 
Soniox
stt-rt-v5
Measured 2026-07-03
WER · batch
7.5%
95% CI 4.8–10.7 · n=50
WER · stream
7.3%
WER · conversational
13.1%
Was 36.5% until a teardown bug of ours stopped finalizing unheard audio.
Finalize
78ms
p50–p90 · us-east4 · n=30
Time to first token
1.04s
p50–p90 · us-east4
Cost / min
$0.002
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/stt/soniox-stt-rt-v5)
HTML
<a href="https://benchmarks.speko.ai/stt/soniox-stt-rt-v5"><img src="https://benchmarks.speko.ai/badge/stt/soniox-stt-rt-v5.svg" alt="Speko stt rank"></a>
URL
https://benchmarks.speko.ai/stt/soniox-stt-rt-v5