Microsoft MAI-Transcribe 2
Microsoft AI's multilingual transcription model, which covers 60 languages with automatic language detection and returns plain text.
From Microsoft, MAI-Transcribe 2 is a cloud speech-to-text model. It transcribes spoken audio into written text. It handles multiple spoken languages. It runs through OpenRouter using your own API key, from about $0.0017 per minute of audio.
- Released
- Sep 2026
- Pricing
- $0.0017 per minute of audio
- Type
- Speech-to-text
- Languages
- Multilingual
Samples
Transcribed by MAI-Transcribe 2 via OpenRouter. The same three clips go to every speech-to-text model in the catalog, so the only thing that changes between two models’ transcripts is the model. The clips are synthetic speech made with ElevenLabs v4, and a word that differs from the spoken script is underlined. The numbers clip is left unmarked, since “12” and “twelve” are both right.
Baseline accuracy and punctuation on clean speech
Thanks for joining on such short notice. We moved the launch to Thursday, so could you send me your notes before lunch? I will share the final schedule with everyone tomorrow morning.
Thanks for joining on such short notice. We moved the launch to Thursday, so could you send me your notes before lunch? I will share the final schedule with everyone tomorrow morning.
How dates, amounts, units and a surname are written out
Invoice 4471 is due on March 3rd, 2027. The total comes to $1,249.50 for 12 units, and the parcel weighs 2.5 kilograms. Please call Dr. Elena Markovic at 9:45 a.m. to confirm.
Invoice 4471 is due on March 3, 2027. The total comes to $1,249.50 for 12 units, and the parcel weighs 2.5 kilograms. Please call Dr. Elena Markovich at 9:45 AM to confirm.
Background noise, a second accent, speaker changes
Excuse me, is this seat taken? No, go ahead. Are you heading to the conference as well? I am. Do you know which stop it is? The one after the river, I think. We can walk over together.
Excuse me, is this seat taken? No, go ahead. Are you heading to the conference as well? I am. Do you know which stop it is? The one after the river, I think. We can walk over together.
Microsoft
Microsoft builds the open-weight Phi family of small language models for reasoning, math and code. Microsoft AI also makes MAI-Transcribe, a speech-to-text model that covers 60 languages.
azure.microsoft.com/products/phi ↗Microsoft AI's precision image model for design-ready visuals, which generates from a prompt and edits or composes from up to five reference images.
The lower-latency, lower-cost member of Microsoft AI's MAI-Image 2.6 family, built for high-throughput image generation and editing from up to five reference images.
The highest-fidelity tier of Microsoft AI's MAI-Image 2.5 family, producing photorealistic and artistic images from a prompt or one reference image.
Microsoft AI's image model for photorealistic and artistic images from a prompt or one reference image, in seven aspect ratios.
Microsoft AI's highest-fidelity text-to-speech model, with detailed prosody and a consistent speaker over long passages. It reads in 23 languages through preset voices across 28 locales, and the voice you pick sets the language.
Microsoft AI's low-latency text-to-speech model, built for real-time responsiveness. It reads in 23 languages through the same preset voices as MAI-Voice-2.1, across 28 locales, and the voice you pick sets the language.