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

Covered by 3 sources
Read onSiliconANGLE· 5 min
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.

Also covered by 2 sources

More on this story


More in Machine Learning