MAI-Transcribe-2: model ids and price

How to call it

5 ways to use MAI-Transcribe-2, with the model id each provider expects.

Providers, model ids, endpoints and docs for MAI-Transcribe-2
Provider	Model id	Endpoint	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`	learn.microsoft.com
Azure Speech (previous version)	`MAI-Transcribe-1.5`		learn.microsoft.com
Azure Voice Live (input transcription)	`MAI-Transcribe-2`		learn.microsoft.com
OpenRouter	`microsoft/mai-transcribe-2`	`https://openrouter.ai/api/v1/audio/transcriptions`
Web app (MAI Playground)			playground.microsoft.ai

Pricing

Prices for MAI-Transcribe-2
Per hour	$0.10

As published: “USD per hour of audio (limited-time promotional price through end of 2026; MAI-Transcribe-1.5 was $0.36/hr)”.

Source: microsoft.ai, checked 29 September 2026.

Specs

Input: Audio
Output: Text
Context window: Not published
Max output: Not published
Open weights: No
Licence: Proprietary
Released: 3 September 2026
Status: Preview
Type: Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

#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: microsoft.ai
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: microsoft.ai
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: learn.microsoft.com

Notes

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.

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/