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: 411x realtime, lowest market price(13 posts)→
More from Models
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21
- qev-0.8B: a tiny local decision model that picks moves in 3.5ms on 1.3GB — fajfas3 · 2026-10-21
- Gemini 3.1 Pro is too ledger-pilled to play two truths and a lie, and it's delightful — mimi10v3 · 2026-10-21