Microsoft unveils MAI-Transcribe-2-Streaming for real-time transcription in 60 languages
Summary
Microsoft unveils MAI-Transcribe-2-Streaming, its first real-time transcription model for 60 languages, saying it produces text within 100 milliseconds for live dictation and subtitles, alongside new MAI-Voice-2.1 text-to-speech models covering 23 languages and 26 locales.
Key Points
- Microsoft unveils MAI-Transcribe-2-Streaming, its first streaming transcription model, delivering real-time transcripts in 60 languages.
- Microsoft says the model returns text within 100 milliseconds of receiving audio and is twice as fast as its closest competitors for real-time dictation and subtitling.
- Microsoft also launches MAI-Voice-2.1 and MAI-Voice-2.1-Flash, adding text-to-speech support for 23 languages and 26 locales.