Microsoft releases VibeVoice-ASR, an open speech-to-text model | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Microsoft releases VibeVoice-ASR, an open speech-to-text model (github.com/microsoft)
		3 points by putlake 16 days ago \| hide \| past \| favorite \| 1 comment

putlake 16 days ago [–]

VibeVoice-ASR is a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact