{"schema":"postcutoff/event@1","as_of":"2026-11-19T22:11:00+01:00","url":"https://postcutoff.com/e/2026-10-01-microsoft-mai-transcribe-2-streaming-voice-2-1/","md":"https://postcutoff.com/e/2026-10-01-microsoft-mai-transcribe-2-streaming-voice-2-1/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":"2026-10-01-microsoft-mai-transcribe-2-streaming-voice-2-1","date":"2026-10-01","date_precision":"day","short_title":"Microsoft AI launches MAI-Transcribe-2-Streaming and MAI-Voice-2.1 / 2.1-Flash","deck":null,"takeaway":null,"category":"model-release","category_label":"Model releases","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Mustafa Suleyman on X: most accurate real-time transcription model","url":"https://x.com/mustafasuleyman/status/2105699115602677984","type":"official","group":"primary","domain":"x.com"},{"n":2,"title":"Microsoft AI: Our first streaming transcription model","url":"https://microsoft.ai/news/our-first-streaming-transcription-model/","type":"official","group":"primary","domain":"microsoft.ai"},{"n":3,"title":"@MicrosoftAI on X: all three models available today","url":"https://x.com/microsoftai/status/2105693027704390144","type":"official","group":"primary","domain":"x.com"},{"n":4,"title":"Artificial Analysis on X: MAI-Transcribe-2-Streaming #1 on AA-WER Streaming","url":"https://x.com/ArtificialAnlys/status/2105694108736188894","type":"discussion","group":"reactions","domain":"x.com"}],"official":3,"filed":"2026-10-02","updated":"2026-10-02","orgs":["Microsoft"],"title":"Microsoft AI launches MAI-Transcribe-2-Streaming (real-time ASR) and MAI-Voice-2.1 / 2.1-Flash","summary":"On Oct 1, 2026 Microsoft AI released MAI-Transcribe-2-Streaming, its first streaming speech-recognition model (first hypotheses in just over 100 ms, 60 languages, $0.54/hour through year-end), and two text-to-speech models, MAI-Voice-2.1 ($22 per 1M characters) and MAI-Voice-2.1-Flash (150 ms end-to-end, $15 per 1M characters). It extends Microsoft's in-house voice stack beyond OpenAI models.","key_facts":["MAI-Transcribe-2-Streaming: first hypotheses in just over 100 ms; Microsoft claims words appear 2x faster than the closest competitor and #1 accuracy for final and partial transcripts on Artificial Analysis","MAI-Transcribe-2-Streaming: 60 languages with automatic language detection; $0.54 per hour of audio through end of 2026","MAI-Voice-2.1: 23 languages / 26 locales, one voice keeps its native accent across languages, voice cloning with consent guardrails; $22 per 1M characters","MAI-Voice-2.1-Flash: 150 ms end-to-end latency, 55% faster inference; $15 per 1M characters","Availability: Microsoft Foundry, MAI Playground, OpenRouter, Vercel, Azure Voice Live; LiveKit coming soon","Artificial Analysis (Oct 1, ~368k views): #1 of 38 models on AA-WER Streaming, final-transcript WER 2.5% at 0.13 s after end of speech (previous #1 Grok Voice Transcribe 2.0: 2.7% at 0.49 s); first partial transcript 2.5% at 0.12 s. AA puts its $0.54/hour ($9 per 1,000 min) at the high end, above ElevenLabs Scribe v2 Realtime and Deepgram Flux ($6.50)","Mustafa Suleyman (Oct 1, ~311k views): 'most accurate real time transcription model in the world', '55% faster and 60% cheaper than ElevenLabs' (the price claim conflicts with AA's per-hour comparison; the basis of the 60% figure is not stated)"],"key_numbers":[],"tags":["speech","asr","tts","voice","microsoft-ai","realtime"],"science":null,"body_md":"## What happened\n\nMicrosoft AI (Mustafa Suleyman's group) shipped a low-latency streaming version of MAI-Transcribe-2 plus an updated voice-generation pair.\nAll three were available on launch day. Benchmark claims are Microsoft's own, citing Artificial Analysis.\n\n## Why it matters\n\nReal-time transcription and TTS are the building blocks of voice agents. Microsoft now offers its own models for both at low prices,\ncompeting with OpenAI, ElevenLabs and Deepgram.","disputed":[],"related":[{"id":"2026-09-03-mai-transcribe-2","url":"https://postcutoff.com/e/2026-09-03-mai-transcribe-2/","date":"2026-09-03","date_precision":"day","short_title":"Microsoft launches MAI-Transcribe-2, claiming the most accurate and cheapest speech recognition at $0.10/hour","deck":null,"takeaway":null,"category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Microsoft"]},{"id":"2026-07-25-azure-realtime-voice-live","url":"https://postcutoff.com/e/2026-07-25-azure-realtime-voice-live/","date":"2026-07-25","date_precision":"day","short_title":"Microsoft makes its own Azure Realtime speech-to-speech model generally available in the Voice Live API","deck":null,"takeaway":"Microsoft now offers a first-party realtime voice model next to OpenAI's inside its own voice-agent platform.","category":"product","category_label":"Products","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Microsoft"]},{"id":"2026-06-02-microsoft-mai-models-build-2026","url":"https://postcutoff.com/e/2026-06-02-microsoft-mai-models-build-2026/","date":"2026-06-02","date_precision":"day","short_title":"Microsoft launches seven in-house MAI models at Build 2026, led by MAI-Thinking-1","deck":null,"takeaway":"Coming weeks after the renegotiated OpenAI deal, the launch shows Microsoft hedging its OpenAI dependence with a first-party model family deployed across its biggest products.","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Microsoft"]}],"people":[{"id":"mustafa-suleyman","name":"Mustafa Suleyman","url":"https://postcutoff.com/person/mustafa-suleyman/"}],"posts":[{"id":"x-microsoftai-2105693027704390144","title":"“All three models are available today! Learn more details here:”","url":"https://postcutoff.com/p/x-microsoftai-2105693027704390144/"},{"id":"2026-10-01-artificialanlys-mai-transcribe-2-streaming","title":"Artificial Analysis: MAI-Transcribe-2-Streaming takes #1 on AA-WER Streaming","url":"https://postcutoff.com/p/2026-10-01-artificialanlys-mai-transcribe-2-streaming/"},{"id":"2026-10-01-mustafasuleyman-mai-transcribe-2-streaming","title":"Suleyman: 'the most accurate real time transcription model in the world'","url":"https://postcutoff.com/p/2026-10-01-mustafasuleyman-mai-transcribe-2-streaming/"}],"videos":[],"models":[{"id":"mai-transcribe-2-streaming","name":"MAI-Transcribe-2-Streaming","url":"https://postcutoff.com/m/mai-transcribe-2-streaming/"},{"id":"mai-voice-2-1","name":"MAI-Voice-2.1 / MAI-Voice-2.1-Flash","url":"https://postcutoff.com/m/mai-voice-2-1/"}],"changes":[{"date":"2026-10-02","type":"edit","text":"Added Artificial Analysis results and Suleyman's post"},{"date":"2026-10-02","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-02","run":null,"sources_read":null,"updated":"2026-10-02","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":123,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":93,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":184,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":123,"in_training_data":false}],"short_url":null}