MAI Transcribe 2

Changes from previous version

Expands from 43 to 60 languages versus MAI Transcribe 1.5, adds diarization and word-level timestamps, cuts hourly price from $0.36 to $0.10 through 2026-12-31, and halves cited inference time for 1 hour of audio from 20 seconds to 10 seconds.

Release Summary

Microsoft AI's most capable speech-to-text model, in public preview on Microsoft Foundry, Azure Speech, MAI Playground, and OpenRouter. Adds speaker diarization, word-level timestamps, clean vs verbatim styles, code switching, and automatic language detection across 60 languages. Microsoft reports 5.2% average WER on FLEURS across 60 languages (3.4% on the top 25) versus 3.7% top-25 WER and 43 languages for MAI Transcribe 1.5. Beats Gemini 3.5 Transcribe, GPT-Transcribe, Whisper V3-Large, and Scribe v2 on cited evals. Launch price $0.10 per hour of audio through 2026-12-31 (1.5 is $0.36/hour). Microsoft cites 10x batch speed vs GPT-Transcribe, 7x vs Scribe v2, and 5x vs Gemini 3.5 Transcribe.

Timeline

Other MAI Transcribe versions