Microsoft Unveils MAI-Transcribe-2-Streaming and New MAI-Voice Models for Real-Time Speech AI
Covered by 3 sources

Microsoft introduced MAI-Transcribe-2-Streaming, a real-time transcription model supporting over 60 languages with low latency and high accuracy, alongside two new MAI-Voice text-to-speech models designed for natural conversational AI. These models are available on platforms including Microsoft Foundry and Vercel AI Gateway, emphasizing data security and rapid response for voice applications.

