Microsoft AI streaming transcription gets its first real-time model: MAI-Transcribe-2-Streaming launches at $0.54 per audio hour through Microsoft Foundry and Azure AI Speech, completing a voice agent ...

Microsoft Corp. today expanded its MAI artificial intelligence model family with its first streaming transcription model, debuting alongside two others focused on text-to-speech. They’re designed for ...

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.

Streaming, taking the #1 spot for Final Transcript accuracy and First Partial Transcript accuracy on AA-WER Streaming with 2.5% WER at 0.13s after end of speech MAI-Transcribe-2-Streaming is ...

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 ...