{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/mai-transcribe-2/","md":"https://postcutoff.com/m/mai-transcribe-2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"mai-transcribe-2","name":"MAI-Transcribe-2","org":"Microsoft","family":"MAI-Transcribe","released":"2026-09-03","status":"preview","type":"audio/speech","modality_in":["audio"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_hour":0.1,"unit":"USD per hour of audio (limited-time promotional price through end of 2026; MAI-Transcribe-1.5 was $0.36/hr)","source":"https://microsoft.ai/models/mai-transcribe-2/"},"price_line":"$0.10 per hour","access":[{"provider":"Azure Speech in Microsoft Foundry (Fast Transcription API, enhancedMode)","model_id":"MAI-Transcribe-2","endpoint":"https://{resource}.cognitiveservices.azure.com/speechtotext/transcriptions:transcribe?api-version=2025-10-15","docs":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe"},{"provider":"Azure Speech (previous version)","model_id":"MAI-Transcribe-1.5","docs":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe"},{"provider":"Azure Voice Live (input transcription)","model_id":"MAI-Transcribe-2","docs":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe"},{"provider":"OpenRouter","model_id":"microsoft/mai-transcribe-2","endpoint":"https://openrouter.ai/api/v1/audio/transcriptions"},{"provider":"Web app (MAI Playground)","url":"https://playground.microsoft.ai/"}],"capabilities":[{"name":"#1 on FLEURS across 60 languages (claimed)","detail":"Microsoft reports 5.2% average WER over 60 FLEURS languages (3.4% on top-25) and #2 on the Artificial Analysis WER leaderboard.","first":false,"discovered":"launch","source":"https://microsoft.ai/news/mai-transcribe-2-is-the-fastest-most-accurate-and-cheapest-speech-recognition-model-in-the-world/"},{"name":"Very fast batch transcription","detail":"Claims ~10x faster than GPT-Transcribe (1 hour of audio in ~10 s), 7x vs Scribe v2, 5x vs Gemini 3.5.","first":false,"discovered":"launch","source":"https://microsoft.ai/news/mai-transcribe-2-is-the-fastest-most-accurate-and-cheapest-speech-recognition-model-in-the-world/"},{"name":"Diarization, word timestamps, keyword biasing, clean/verbatim styles","detail":"New in v2: speaker diarization, word-level timestamps, phrase-list biasing, code-switching (e.g. Hinglish) and verbatim vs clean transcripts.","first":false,"discovered":"launch","source":"https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-transcribe"}],"entry":"2026-09-03-mai-transcribe-2","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.","verified":"2026-09-29","body_md":"```bash\ncurl 'https://YOUR_RESOURCE.cognitiveservices.azure.com/speechtotext/transcriptions:transcribe?api-version=2025-10-15' \\\n  -H \"Ocp-Apim-Subscription-Key: $SPEECH_KEY\" -F 'audio=@meeting.wav' \\\n  -F 'definition={\"enhancedMode\":{\"enabled\":true,\"model\":\"MAI-Transcribe-2\"},\"diarization\":{\"enabled\":true}}'\n```\n\nSources: 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/","page_url":"https://postcutoff.com/m/mai-transcribe-2/","standing":{"kind":"speech and audio","newer_count":28,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"mai-voice-2","name":"MAI-Voice-2 / MAI-Voice-2-Flash","org":"Microsoft","released":"2026-06-02","page_url":"https://postcutoff.com/m/mai-voice-2/"},"after":{"id":"mai-voice-2-1","name":"MAI-Voice-2.1 / MAI-Voice-2.1-Flash","org":"Microsoft","released":"2026-10-01","page_url":"https://postcutoff.com/m/mai-voice-2-1/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}