kapynAI / Models

Microsoft AI releases new transcription and text-to-speech models for voice agents

Microsoft AI introduces MAI-Transcribe-2-Streaming for real-time transcription and voice agents. The release expands Microsoft's audio intelligence stack, providing developers with low latency speech capabilities. These new voice models enable more responsive conversational AI applications and real-time transcription workflows.

The Decoder·Oct 2, 2026

Opening Kapyn…