VibeVoice Technical Report

TL;DR

VibeVoice is a new speech synthesis model that uses diffusion and a novel tokenizer to generate long-form, multi-speaker speech efficiently, achieving high fidelity and extended duration.

Contribution

It introduces a continuous speech tokenizer that outperforms existing models in compression and efficiency, enabling long-duration, multi-speaker speech synthesis.

Findings

80x data compression improvement over Encodec

Supports up to 90-minute long-form speech

Synthesizes speech for up to 4 speakers

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.