Developing story · 2 episodes · 1 Oct to 4 Oct
Microsoft's Real-Time Voice AI Evolution
Microsoft has been rolling out new real-time voice AI models for developers, culminating in a system that transcribes speech before the speaker finishes. The latest episode shows the technology advancing toward near‑instantaneous transcription, positioning Microsoft as a leader in conversational AI while raising questions about latency and user experience.
-
AI that turns into text before you finish speaking: What changes with Microsoft's new voice AI?
Microsoft announced on October 1, 2026 a new suite of voice AI tools that can return text while a speaker is still talking. The transcription service, called MAI-Transcribe-2-Streaming, shows…
1 source -
Microsoft launches three real-time voice AI models for developers
Microsoft released three new AI voice models on Thursday. MAI-Transcribe-2-Streaming converts live speech to text in 60 languages within milliseconds, enabling real-time responses. MAI-Voice-2.1…
10 sources
Who and what
MicrosoftMicrosoft Foundry ModelsMicrosoft Frontier CompanyMAI-Transcribe-2-StreamingMAI-Voice-2.1MAI-Voice-2.1-FlashNaomi Moneypenny