← Speech-to-Text
Inworld
Realtime STT-1
Measured 2026-10-01
Build voice agents on Speko →Realtime STT-1 is measured here for comparison — it is not one of the models Speko routes.
WER · batch
3.3%
WER · streaming
Read speech
27.92%
Conversation
12.14%
Details
Read speech
n=1541 · FLEURS test+dev+train · vendor-direct
188 of 1541 clips came back empty, scored as all-deletion.
Conversation
10.4–14.4% · EdAcc n=283 · 60 speakers, 2 passes, 2026-10-01
Finalize
670ms
p50–p90 · US East · n=200 · vendor-direct · ±17%
Time to first token
1.32s
p50–p90 · US East · n=200 · vendor-direct · ±8%
Cost / min
$0.0025
On-demand $0.15/hr. The $0.10/hr headline needs a paid Creator subscription.
Share this result
Embed the live badge
Markdown
[](https://speko.ai/benchmarks/stt/inworld-realtime-stt-1)
HTML
<a href="https://speko.ai/benchmarks/stt/inworld-realtime-stt-1"><img src="https://speko.ai/benchmarks/badge/stt/inworld-realtime-stt-1.svg" alt="Speko stt rank"></a>
URL
https://speko.ai/benchmarks/stt/inworld-realtime-stt-1