# SynthVC: Leveraging Synthetic Data for End-to-End Low Latency Streaming Voice Conversion

arXiv: https://arxiv.org/abs/2510.09245 · HTML: https://mlsanity.com/paper/2510.09245/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2025.

## Built on by (most cited first, 2 of 2)

- [MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora](https://mlsanity.com/paper/2604.11552/) (2026)
- [From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data](https://mlsanity.com/paper/2606.08843/) (2026)

## Abstract (arXiv)

Voice Conversion (VC) aims to modify a speaker's timbre while preserving linguistic content. While recent VC models achieve strong performance, most struggle in real-time streaming scenarios due to high latency, dependence on ASR modules, or complex speaker disentanglement, which often results in timbre leakage or degraded naturalness. We present SynthVC, a streaming end-to-end VC framework that directly learns speaker timbre transformation from synthetic parallel data generated by a pre-trained zero-shot VC model. This design eliminates the need for explicit content-speaker separation or recognition modules. Built upon a neural audio codec architecture, SynthVC supports low-latency streaming inference with high output fidelity. Experimental results show that SynthVC outperforms baseline streaming VC systems in both naturalness and speaker similarity, achieving an end-to-end latency of just 77.1 ms.