You want to transcribe meeting remarks in real time. You want to respond to inquiries with voice. Both are uses for voice AI, ...

Microsoft AI Releases Three New Speech Transcription and Text-to-Speech Models SimultaneouslyArticle Summary) On October 1, 2026, Microsoft AI simultaneously released three new speech-related models ...

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 MAI voice models add live transcription in 60 languages, plus two multilingual speech generators for developers ...

Microsoft has introduced the MAI-Transcribe-2-Streaming model, acclaimed for its accuracy, alongside multilingual MAI-Voice 2.1 models for enhanced conversational agents.

Microsoft has launched three new artificial intelligence models that can be used to power customer service agents, ...

Streaming, taking the #1 spot for Final Transcript accuracy and First Partial Transcript accuracy on AA-WER Streaming with ...

The text-to-speech avatar is a new feature with vision capabilities that empowers customers to generate synthetic videos of a 2D photorealistic avatar speaking, Azure AI Speech said in a Wednesday ...

Microsoft announced this week that it wrapped up the development of VALL-E 2, the second iteration of its VALL-E artificial intelligence speech generator. According to the researchers behind the new ...

Streaming, a new model for real-time transcription. Microsoft says it ranks first for accuracy on Artificial Analysis. The ...