← Speech-to-Text
OpenAI
GPT-4o-mini Transcribe
Measured 2026-10-01
Run GPT-4o-mini Transcribe on Speko →One API, every model on this board.
WER · batch
2.7%
WER · streaming
Read speech
5.69%
Conversation
20.60%
Details
Read speech
n=1541 · FLEURS test+dev+train · vendor-direct
Conversation
17.1–24.3% · EdAcc n=283 · 60 speakers, 2 passes, 2026-10-01
Finalize
822ms
p50–p90 · US East · n=200 · vendor-direct · ±9%
Time to first token
6.33s
p50–p90 · US East · n=200 · vendor-direct · ±10%
Cost / min
$0.003
Share this result
Embed the live badge
Markdown
[](https://speko.ai/benchmarks/stt/openai-gpt-4o-mini-transcribe)
HTML
<a href="https://speko.ai/benchmarks/stt/openai-gpt-4o-mini-transcribe"><img src="https://speko.ai/benchmarks/badge/stt/openai-gpt-4o-mini-transcribe.svg" alt="Speko stt rank"></a>
URL
https://speko.ai/benchmarks/stt/openai-gpt-4o-mini-transcribe