From Cloud Wars · Kieron Allen · · 50s
Microsoft Launches Real-Time Transcription Model
Microsoft releases streaming transcription tech for conversational AI.
In brief
Microsoft releases streaming transcription tech for conversational AI. Microsoft launched MAI Transcribe to Streaming, a real-time speech-to-text model that operates in 60 languages with continuous language detection and ranks number one for accuracy in both final and partial transcripts. Originally reported by Cloud…
Microsoft Launches MAI Transcribe to Streaming
Microsoft has launched MAI Transcribe to Streaming, a real-time speech-to-text model and Microsoft’s first model in the streaming transcription category.
60 Languages with Continuous Detection
It operates in 60 languages with continuous automatic language detection and ranks number one for accuracy in both final and partial transcripts.
Voice Models for Conversational Experiences
Microsoft is also launching two new voice models, MAI Voice 2.1 and MAI Voice 2.1 Flash, which pair with the transcription model for conversational ai.
“Together, they give users the fast and fluid building blocks to create conversational experiences with no compromise on accuracy or voice quality.”
The headline
Microsoft launched MAI Transcribe to Streaming, a real-time speech-to-text model that operates in 60 languages with continuous language detection and ranks number one for accuracy in both final and partial transcripts.
