← Speech-to-Text 
Batch lane
Microsoft
MAI-Transcribe-2
Vendor-direct Azure Speech fast transcription (enhancedMode), eastus / FLEURS n=50 + EdAcc n=82 / 2026-09-03
* Conditional
Batch API only — no streaming socket, so nothing on the live path is measured here.
WER · batch
2.3%
Same pass reproduced the Nova-3 anchor at its published 11.96%.
WER · stream
-
WER · conversational
-
Finalize
-
Time to first token
-
Cost / min
$0.0017
$0.10 per hour of audio, a launch price with no stated end date.
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/stt/microsoft-mai-transcribe-2)
HTML
<a href="https://benchmarks.speko.ai/stt/microsoft-mai-transcribe-2"><img src="https://benchmarks.speko.ai/badge/stt/microsoft-mai-transcribe-2.svg" alt="Speko stt rank"></a>
URL
https://benchmarks.speko.ai/stt/microsoft-mai-transcribe-2