VIBEVOICE-ASR Technical Report

TL;DR

VibeVoice-ASR is a versatile, end-to-end speech understanding framework capable of processing long-form audio with multi-language and code-switching support, improving accuracy through prompt-based context injection.

Contribution

It introduces VibeVoice-ASR, a single-pass, multi-task framework for long-form audio that unifies recognition, diarization, and timestamping, with novel context injection for domain adaptation.

Findings

Supports up to 60 minutes of audio in a single pass

Handles over 50 languages without explicit language setting

Improves accuracy with prompt-based context injection

Abstract

This report presents VibeVoice-ASR, a general-purpose speech understanding framework built upon VibeVoice, designed to address the persistent challenges of context fragmentation and multi-speaker complexity in long-form audio (e.g., meetings, podcasts) that remain despite recent advancements in short-form speech recognition. Unlike traditional pipelined approaches that rely on audio chunking, VibeVoice-ASRsupports single-pass processing for up to 60 minutes of audio. It unifies Automatic Speech Recognition, Speaker Diarization, and Timestamping into a single end-to-end generation task. In addition, VibeVoice-ASR supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. Furthermore, we introduce a prompt-based context injection mechanism that allows users to supply customized conetxt, significantly improving accuracy on domain-specific terminology and polyphonic character disambiguation.