VIBEVOICE-ASR Technical Report
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.
Cite
@article{arxiv.2601.18184,
title = {VIBEVOICE-ASR Technical Report},
author = {Zhiliang Peng and Jianwei Yu and Yaoyao Chang and Zilong Wang and Li Dong and Yingbo Hao and Yujie Tu and Chenyu Yang and Wenhui Wang and Songchen Xu and Yutao Sun and Hangbo Bao and Weijiang Xu and Yi Zhu and Zehua Wang and Ting Song and Yan Xia and Zewen Chi and Shaohan Huang and Liang Wang and Chuang Ding and Shuai Wang and Xie Chen and Furu Wei},
journal= {arXiv preprint arXiv:2601.18184},
year = {2026}
}