Microsoft launches MAI-Transcribe-2-Streaming, a model for low-latency, real-time transcripts, and two new voice models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash (Microsoft AI)

Microsoft AI has launched MAI-Transcribe-2-Streaming, a new model designed for low-latency, real-time transcripts. Additionally, two new voice models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash, have been introduced. These MAI-Transcribe and MAI-Voice models are characterized by their accuracy, speed, and low cost, offering chart-topping audio understanding and generation capabilities for developing advanced conversational voice agents.