Inworld
Realtime STT-1
Measured 2026-07-03
* Conditional
Finalizes eagerly — ~1 in 5 turns commit before speech ends.
WER · batch
3.3%
WER · stream
3.6%
WER · conversational
11.8%
KNOWN FAILURE MODE, EXCLUDED FROM THIS NUMBER. On one corpus clip its decode collapsed into a repetition loop — 29 reference words became 339 of "co", more word errors than it makes across the rest of the corpus combined. That clip is excluded for EVERY provider, so it is absent from all seventeen rows. A caller can trigger this, and an agent would answer the garbage.
Finalize
139ms
p50–p90 · us-east4 · n=50
Time to first token
1.21s
p50–p90 · us-east4
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
[](https://benchmarks.speko.ai/stt/inworld-realtime-stt-1)
<a href="https://benchmarks.speko.ai/stt/inworld-realtime-stt-1"><img src="https://benchmarks.speko.ai/badge/stt/inworld-realtime-stt-1.svg" alt="Speko stt rank"></a>
https://benchmarks.speko.ai/stt/inworld-realtime-stt-1