DEVOURED
Microsoft's first streaming transcription model debuts at No. 1 on Artificial Analysis
Microsoft launched its first streaming transcription model, MAI-Transcribe-2-Streaming, alongside new voice generation models MAI-Voice-2.1 and MAI-Voice-2.1-Flash.
What: The new MAI-Transcribe-2-Streaming offers low-latency, real-time transcription across 60 languages with continuous language detection. MAI-Voice-2.1 supports 23 languages and 26 locales, maintaining consistent voice profiles across different regions.
Why it matters: This indicates Microsoft is prioritizing real-time conversational infrastructure to compete with low-latency offerings from ElevenLabs and OpenAI.
Original article
Microsoft's MAI-Transcribe and MAI-Voice models provide accurate, fast, low-cost, and chart-topping audio understanding and generation. The company has launched MAI-Transcribe-2-Streaming along with MAI‑Voice‑2.1 and MAI‑Voice‑2.1-Flash, giving users fast and fluid building blocks to create conversational experiences with no compromise on accuracy or voice quality. MAI-Transcribe-2-Streaming delivers low-latency, real-time transcripts in 60 languages, all while supporting automatic, continuous language detection. MAI-Voice-2.1 supports 23 languages and 26 locales, allowing users to keep a single voice everywhere.
Explore all 52 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi