# MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

arXiv: https://arxiv.org/abs/2510.08392 · HTML: https://mlsanity.com/paper/2510.08392/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2025.

## Built on by (most cited first, 6 of 6)

- [Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data](https://mlsanity.com/paper/2603.07534/) (2026)
- [X-VC: Zero-shot Streaming Voice Conversion in Codec Space](https://mlsanity.com/paper/2604.12456/) (2026)
- [MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora](https://mlsanity.com/paper/2604.11552/) (2026)
- [FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation](https://mlsanity.com/paper/2606.09141/) (2026)
- [The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints](https://mlsanity.com/paper/2608.07980/) (2026)
- [AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation](https://mlsanity.com/paper/2610.14697/) (2026)

## Abstract (arXiv)

Zero-shot voice conversion (VC) aims to transfer timbre from a source speaker to any unseen target speaker while preserving linguistic content. Growing application scenarios demand models with streaming inference capabilities. This has created a pressing need for models that are simultaneously fast, lightweight, and high-fidelity. However, existing streaming methods typically rely on either autoregressive (AR) or non-autoregressive (NAR) frameworks, which either require large parameter sizes to achieve strong performance or struggle to generalize to unseen speakers. In this study, we propose MeanVC, a lightweight and streaming zero-shot VC approach. MeanVC introduces a diffusion transformer with a chunk-wise autoregressive denoising strategy, combining the strengths of both AR and NAR paradigms for efficient streaming processing. By introducing mean flows, MeanVC regresses the average velocity field during training, enabling zero-shot VC with superior speech quality and speaker similarity in a single sampling step by directly mapping from the start to the endpoint of the flow trajectory. Additionally, we incorporate diffusion adversarial post-training to mitigate over-smoothing and further enhance speech quality. Experimental results demonstrate that MeanVC significantly outperforms existing zero-shot streaming VC systems, achieving superior conversion quality with higher efficiency and significantly fewer parameters. Audio demos and code are publicly available at https://aslp-lab.github.io/MeanVC.