VibeVoice-ASR
microsoft · Kit
An 8.7B speech-to-text model from Microsoft Research that transcribes up to 60 minutes in one pass, saying who spoke, when and what, with optional hotwords and…
New
microsoft · Kit
An 8.7B speech-to-text model from Microsoft Research that transcribes up to 60 minutes in one pass, saying who spoke, when and what, with optional hotwords and…
microsoft · Kit
Microsoft’s open-source family of voice AI models. VibeVoice-ASR transcribes up to 60 minutes of audio in one pass, with speakers and timestamps. VibeVoice-Rea…