MAI-Transcribe-2
Public preview in Azure Speech. MAI-Transcribe-1.5 (Build 2026-06-02, 43 languages, $0.36/hr) remains available; MAI-Transcribe-1 deprecated 2026-08-20. Standard (post-promo) price not published. Input WAV/MP3/FLAC. Model card: https://microsoft.ai/pdf/MAI-Transcribe-2-Model-Card.pdf. Benchmarks are Microsoft-reported.
- Input
- audio
- Output
- text
- License
- proprietary
- Pricing
- per hour: $0.1 (USD per hour of audio (limited-time promotional price through end of 2026; MAI-Transcribe-1.5 was $0.36/hr)) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Azure Speech in Microsoft Foundry (Fast Transcription API, enhancedMode) | MAI-Transcribe-2 | https://{resource}.cognitiveservices.azure.com/speechtotext/transcriptions:transcribe?api-version=2025-10-15 | docs |
| Azure Speech (previous version) | MAI-Transcribe-1.5 | — | docs |
| Azure Voice Live (input transcription) | MAI-Transcribe-2 | — | docs |
| OpenRouter | microsoft/mai-transcribe-2 | https://openrouter.ai/api/v1/audio/transcriptions | — |
| Web app (MAI Playground) | — | playground.microsoft.ai/ | — |
Notable capabilities (3)
- #1 on FLEURS across 60 languages (claimed): Microsoft reports 5.2% average WER over 60 FLEURS languages (3.4% on top-25) and #2 on the Artificial Analysis WER leaderboard. source
- Very fast batch transcription: Claims ~10x faster than GPT-Transcribe (1 hour of audio in ~10 s), 7x vs Scribe v2, 5x vs Gemini 3.5. source
- Diarization, word timestamps, keyword biasing, clean/verbatim styles: New in v2: speaker diarization, word-level timestamps, phrase-list biasing, code-switching (e.g. Hinglish) and verbatim vs clean transcripts. source
curl 'https://YOUR_RESOURCE.cognitiveservices.azure.com/speechtotext/transcriptions:transcribe?api-version=2025-10-15' \
-H "Ocp-Apim-Subscription-Key: $SPEECH_KEY" -F 'audio=@meeting.wav' \
-F 'definition={"enhancedMode":{"enabled":true,"model":"MAI-Transcribe-2"},"diarization":{"enabled":true}}'
Sources: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe · https://microsoft.ai/models/mai-transcribe-2/ · https://microsoft.ai/news/mai-transcribe-2-is-the-fastest-most-accurate-and-cheapest-speech-recognition-model-in-the-world/
Timeline entry
- Microsoft launches MAI-Transcribe-2, claiming the most accurate and cheapest speech recognition at $0.10/hour ★★★
On 2026-09-03 Microsoft AI released MAI-Transcribe-2, an in-house speech-to-text model for 60 languages with diarization and word timestamps, claiming #1 on FLEURS (5.2% average WER), ~10x faster processing than GPT-Transcribe, and a promotional price of $0.10 per audio hour in Azure Speech /…
Other Microsoft models
Phi-4-Reasoning-Vision-15B · VibeVoice (ASR, ASR-Streaming, ASR-BitNet, Realtime-0.5B TTS) · MAI-Voice-2 / MAI-Voice-2-Flash · Phi-4 (14B)