Microsoft’s New AI Voice Models Could Make Conversations Feel Much More Natural
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.8 Articles
8 Articles
Microsoft AI releases new transcription and text-to-speech models for voice agents
Microsoft AI has released MAI-Transcribe-2-Streaming, a new model for real-time transcription. The article Microsoft AI releases new transcription and text-to-speech models for voice agents appeared first on The Decoder.
Microsoft Launches New AI Models for Faster Real-Time Voice Conversations
Copyright protected content copied from PhoneWorld website. Microsoft has expanded its in-house AI portfolio with three new speech models designed to support faster and more natural real-time voice interactions. The new models are MAI-Transcribe-2-Streaming, MAI-Voice-2.1 and MAI-Voice-2.1-Flash. Microsoft says they are designed to work together for low-latency conversational AI applications, including voice agents and other real-time services. …
Microsoft expands its range of home-made models with MAI-Transcribe-2-Streaming, an AI designed to transcribe speech over the course of the conversation. It supports 60 languages and starts producing text just over 100 ms after receiving audio.
Microsoft launched this Thursday, October 1st MAI-Transcribe-2-Streaming, an AI model that transcribes speech live in 60 languages, accompanied by two new voice synthesis models. According to Microsoft, this first live transcription model of the company is number one in precision on the Artificial Analysis comparison.
Microsoft’s New AI Voice Models Could Make Conversations Feel Much More Natural
Microsoft is making a major push into real-time voice AI with three new models designed to make conversations with AI assistants faster, more natural, and more responsive. The company has launched MAI-Transcribe-2-Streaming, its first streaming transcription model, alongside MAI-Voice-2.1 and MAI-Voice-2.1-Flash for high-quality text-to-speech. Together, the models are designed to reduce the delays that can […]
Microsoft released its real-time transcription AI, "MAI-Transcribe-2-Streaming," on October 1, 2026 (local time). It boasts a lower error rate and shorter latency compared to competing models. Read more...
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
