#Speech-to-Text22/01/2026
Microsoft Unveils VibeVoice-ASR for Long-Form Audio
VibeVoice-ASR offers a unified speech-to-text model for 60-minute audio handling.
Records found: 2
VibeVoice-ASR offers a unified speech-to-text model for 60-minute audio handling.
MedASR is an advanced speech-to-text model optimized for clinical dictation.