The full story · 1 min

A streaming transcription model writes down speech while it is still being spoken, instead of waiting for a recording to end. Live captions and voice agents depend on it.

What Microsoft launched

MAI-Transcribe-2-Streaming supports 60 languages and detects the language by itself, Microsoft says. Developers can use it in Microsoft Foundry, where its documentation says it is in public preview.

The model can power apps that show live captions, or start working on a request before the user has finished speaking, SiliconANGLE writes.

The two voice models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash, speak 23 languages. They cost $22 and $15 per million characters.

Sources1245

Check
Fewest words wrong, live.

Artificial Analysis’s streaming leaderboard, first-partial chart, as we read it on October 2.

What the outside test shows

Artificial Analysis tests streaming models on three sets of recordings. On its chart for the first partial transcript after speech ends, MAI-Transcribe-2-Streaming gets 2.5% of words wrong. The next model shown gets 3.4%.

Microsoft says the model also ranks first for final transcripts there. We checked the first-partial chart only.

The leaderboard shows 32 of 38 models in its default view.

Sources13

Microsoft’s own claims

Microsoft says the model produces its first guesses “in just over 100ms”. In its internal tests, it says, words appear twice as fast as with its closest competitor, which it does not name.

SiliconANGLE and RuntimeWire also report a Microsoft figure of about 320 milliseconds for words to appear. Real response times also depend on the user’s network connection, they note.

The $0.54 per hour price is an introductory offer until the end of 2026, Microsoft and WinCentral say.

Sources1456

Sources

Every fact in this story comes from the sources below. Open them to check our work.

  1. 1
  2. 2
    Primary source · October 1, 2026MAI-Transcribe-2-Streaming overview Microsoft Learn
  3. 3
    Research · October 2, 2026Speech to Text Streaming leaderboard Artificial Analysis
  4. 4
  5. 5
  6. 6

AI desk: Products and agents · published October 2, 2026, 09:26 CEST. This story was generated by AI systems under the editorial rules of Silicon AI News and checked against the sources it links. No person read it before it was published. The site’s owner and editor: Y. D. Daniel, Budapest, Hungary. Found a mistake? Email editor@siliconainews.com. How we report

We count only the page and your answer.Thank you. We counted only this page and your answer.
More: words to know, tags and how to cite this story
Words to know
Transcription
Turning spoken words into written text.
Streaming
Working on speech bit by bit as it arrives, not after it ends.
Public preview
An early version that anyone can try, but that is not final.
Basics explainedWhat do “reasoning” models do differently? Can a model write a whole answer at once?

Microsoft’s live transcription model tops an outside test. Silicon AI News, October 2, 2026. https://siliconainews.com/stories/microsoft-mai-transcribe-streaming