VibeVoice Technical Report

• URL: http://arxiv.org/abs/2508.19205v1
• Date: Tue, 26 Aug 2025 17:09:12 GMT
• Title: VibeVoice Technical Report
• Authors: Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, Yutao Sun, Li Dong, Yi Zhu, Weijiang Xu, Hangbo Bao, Zehua Wang, Shaohan Huang, Yan Xia, Furu Wei,
• Abstract summary: VibeVoice is a model designed to synthesize long-form speech with multiple speakers.<n>We introduce a novel continuous speech tokenizer that, when compared to the popular Encodec model, improves data compression by 80 times.
• Score: 90.14596405668135
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This report presents VibeVoice, a novel model designed to synthesize long-form speech with multiple speakers by employing next-token diffusion, which is a unified method for modeling continuous data by autoregressively generating latent vectors via diffusion. To enable this, we introduce a novel continuous speech tokenizer that, when compared to the popular Encodec model, improves data compression by 80 times while maintaining comparable performance. The tokenizer effectively preserves audio fidelity while significantly boosting computational efficiency for processing long sequences. Thus, VibeVoice can synthesize long-form speech for up to 90 minutes (in a 64K context window length) with a maximum of 4 speakers, capturing the authentic conversational ``vibe'' and surpassing open-source and proprietary dialogue models.

Related papers

• READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation [55.58089937219475]
  We propose READ, the first real-time diffusion-transformer-based talking head generation framework.<n>Our approach first learns highly compressed video latent space via a VAE, significantly reducing the token count to speech generation.<n>We show that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime.
  arXiv  Detail & Related papers  (2025-08-05T13:57:03Z)
• Next Tokens Denoising for Speech Synthesis [51.320443764269726]
  Dragon-FM is a novel text-to-speech (TTS) design that unifies AR and flow-matching.<n>It processes 48 kHz audio tokens in chunks at a compact rate of 12.5 tokens per second.<n>Experiments on podcast datasets demonstrate its capability to efficiently generate high-quality zero-shot podcasts.
  arXiv  Detail & Related papers  (2025-07-30T15:03:36Z)
• DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations [62.00227663434538]
  DRVOICE-7B establishes new state-of-the-art (SOTA) on OpenAudioBench and Big Bench Audio benchmarks.<n>This paper presents DrVoice, a parallel speech-text voice conversation model based on joint autoregressive modeling.
  arXiv  Detail & Related papers  (2025-06-11T02:57:22Z)
• VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model [70.25062476543091]
  VITA-Audio is an end-to-end large speech model with fast audio-text token generation.<n>MCTP module efficiently generates multiple audio tokens within a single model forward pass.<n>Four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality.
  arXiv  Detail & Related papers  (2025-05-06T17:59:53Z)
• Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction [9.101978573666546]
  Baichuan-Audio is an end-to-end audio large language model that seamlessly integrates audio understanding and generation.<n>It features a text-guided aligned speech generation mechanism, enabling real-time speech interaction with both comprehension and generation capabilities.
  arXiv  Detail & Related papers  (2025-02-24T15:16:34Z)
• Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis [7.2129341612013285]
  We introduce Lina-Speech, a model that replaces traditional self-attention mechanisms with emerging recurrent architectures like Gated Linear Attention (GLA) This approach is fast, easy to deploy, and achieves performance comparable to fine-tuned baselines when the dataset size ranges from 3 to 15 minutes.
  arXiv  Detail & Related papers  (2024-10-30T04:50:40Z)
• Sample-Efficient Diffusion for Text-To-Speech Synthesis [31.372486998377966]
  It is based on a novel diffusion architecture, that we call U-Audio Transformer (U-AT) SESD achieves impressive results despite training on less than 1k hours of speech. It synthesizes more intelligible speech than the state-of-the-art auto-regressive model, VALL-E, while using less than 2% the training data.
  arXiv  Detail & Related papers  (2024-09-01T20:34:36Z)
• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• SoundStorm: Efficient Parallel Audio Generation [27.121920017380273]
  We present SoundStorm, a model for efficient, non-autoregressive audio generation. SoundStorm receives as semantic tokens of AudioLM, and relies on bidirectional attention and confidence-based parallel decoding. We demonstrate the ability of our model to scale audio generation to longer sequences by synthesizing high-quality, natural dialogue segments.
  arXiv  Detail & Related papers  (2023-05-16T17:41:25Z)
• Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models [65.18102159618631]
  multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. We propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps.
  arXiv  Detail & Related papers  (2023-01-30T04:44:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.