Microsoft’s new voice AI can start working out what you want before you finish speaking
Microsoft introduced MAI-Transcribe-2-Streaming, MAI-Voice-2.1, and MAI-Voice-2.1-Flash through Microsoft Foundry. These models enable voice agents to generate partial hypotheses within hundreds of milliseconds, refining responses as users continue speaking. The technology aims to eliminate awkward pauses in voice-based customer service interactions.
Key points
- Three new voice models available in Microsoft Foundry platform
- Incremental speech recognition produces partial responses within 'low hundreds of milliseconds'
- Models include streaming transcription, multilingual text-to-speech, and optimized variants for high-volume applications
- Designed to improve responsiveness in voice agent interactions
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The New Stack did the reporting; read the original for the full story.
Read the full story at The New Stack
