← Speech-to-TextGoogle

Chirp 3
Measured 2026-10-01
Build voice agents on Speko →Chirp 3 is measured here for comparison — it is not one of the models Speko routes.
WER · batch
3.9%
WER · streaming
Read speech
5.89%
Conversation
18.43%
Details
Read speech
n=1541 · FLEURS test+dev+train · vendor-direct
Conversation
15.2–21.8% · EdAcc n=283 · 60 speakers, 2 passes, 2026-10-01
Finalize
—
not measured on the vendor-direct regional sweep
Time to first token
—
not measured on the vendor-direct regional sweep
Cost / min
$0.0160
Speech-to-Text V2 Standard, first tier — one rate for streaming, sync and batch. Dynamic Batch Recognition is $0.003.
Share this result
Embed the live badge
Markdown
[](https://speko.com/benchmarks/stt/google-chirp-3)
HTML
<a href="https://speko.com/benchmarks/stt/google-chirp-3"><img src="https://speko.com/benchmarks/badge/stt/google-chirp-3.svg" alt="Speko stt rank"></a>
URL
https://speko.com/benchmarks/stt/google-chirp-3
