Microsoft launches MAI-Transcribe-2-Streaming, its first real-time transcription model
IA en un minuto newsroom · Editor: Jon Elgezabal

In 30 seconds
Microsoft AI has released MAI-Transcribe-2-Streaming, which turns speech into text as people talk in 60 languages, Spanish included, with its first output arriving in a little over 100 milliseconds. Two new voices arrive with it, MAI-Voice-2.1 and its Flash version, able to imitate a speaker after hearing just seconds of recording. Transcription costs $0.54 per hour at launch and is in preview in Microsoft Foundry.
On October 1, Microsoft AI, the team that builds Microsoft's own models (MAI), introduced MAI-Transcribe-2-Streaming, a model that turns speech into text while the person is speaking, without waiting for the sentence to end. It works in 60 languages, including Spanish, and automatically detects the language being spoken.
According to Microsoft, it returns its first results in just over 100 milliseconds and ranks number 1 for accuracy on Artificial Analysis, a website that compares AI models. This means a voice agent can start reasoning or using tools before the customer has finished speaking.
It comes with two new voices (models that turn text into speech): MAI-Voice-2.1, which speaks 23 languages with the same voice and a native accent in each one, and MAI-Voice-2.1-Flash, the version built for high volume and fast responses. Both can clone a voice from a few seconds of audio and include consent guardrails to prevent misuse.
Published prices: $0.54 per hour of audio for transcription, an introductory price through the end of the year; $22 per million characters for MAI-Voice-2.1 and $15 for the Flash version.
All three models are available in Microsoft Foundry, Microsoft's platform for building AI applications. The transcription model is in public preview: it can be used from any country, it is served from the Sweden Central region and Microsoft does not yet recommend it for production.
Why it matters · analysis and opinion
Microsoft's first transcription model that does not wait for the sentence to end: the text appears while the person is still speaking.That head start is what a voice agent needs to avoid awkward silences on a call, because it can start looking up data or preparing the answer before the customer finishes. Understanding Spanish and detecting the language on its own makes it interesting for contact centers with customers in several countries. The voices that come with it complete the loop, although cloning a voice from a few seconds of audio demands being very clear about the owner's permission. Microsoft does not yet recommend it for production and the top accuracy ranking is the company's own claim: today it is good for a pilot, not for replacing what already works.
Official source: Microsoft AI · Written with the help of AI: how we make the news


