Hosted on MSN
Microsoft ships first streaming transcription model, completing voice agent pipeline on Foundry
Microsoft released its first real-time speech-to-text model on October 1, 2026, alongside two new voice-generation options — and for developers building conversational AI, the three models together ...
Microsoft AI's MAI-Transcribe-2-Streaming ranks #1 on Artificial Analysis with 2.5% WER at 0.13s, 60 languages, $0.54 per hour.
Microsoft describes MAI-Transcribe-2-Streaming as delivering low-latency, real-time transcripts in 60 languages with automatic, continuous language detection. The company said the model ranks No. 1 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results