Microsoft's MAI-Transcribe-2 hits 2.0% WER at 411x real time for $1.67 per 1,000 minutes

ArtificialAnlys · x · 2026-09-03

Microsoft AI released MAI-Transcribe-2, ranking #2 on the Artificial Analysis word error rate leaderboard with 2.0% AA-WER, behind Alibaba's Fun-Realtime-ASR-preview (1.7%) and ahead of ElevenLabs Scribe v2 (2.2%) and Smallest AI Pulse Pro (2.4%).

It runs at 411x real time — about 1.5x Pulse Pro and 7x+ Scribe v2 — and costs $1.67 per 1,000 minutes ($0.10/hour via Microsoft Foundry), less than half the price of Scribe v2 ($3.67), Pulse Pro ($4), or Gemini 3.5 Transcribe ($5).

Language support expands from 43 to 60 languages, with new speaker diarization, word-level timestamps, and clean/verbatim transcription styles, placing it on the accuracy-speed Pareto frontier.

Related event: Microsoft Launches MAI-Transcribe-2: Faster, Second-Most Accurate, and Cheapest in Class(7 posts)→

Original post →

More from Models

Models channel →