Microsoft targets ultra-realistic voice agents with its first streaming transcription model

SiliconANGLE · 1 week ago · 8 ● 5 sources

Microsoft released MAI-Transcribe-2-Streaming along with two new text-to-speech models to help developers build faster, more natural voice agents with live transcription. MAI-Transcribe-2-Streaming costs 54 cents per audio hour and begins returning transcript hypotheses within 320 milliseconds on average. The update shifts voice-agent development toward streaming captions and earlier processing while letting builders trade off latency and cost via the separate transcription and speech models.