| title: RVCBench — Voice Cloning & Protection Demo | |
| emoji: 🎙️ | |
| colorFrom: blue | |
| colorTo: indigo | |
| sdk: docker | |
| pinned: true | |
| license: cc0-1.0 | |
| short_description: Voice cloning attacks vs. audio protection methods | |
| tags: | |
| - audio | |
| - voice-cloning | |
| - text-to-speech | |
| - speaker-privacy | |
| - audio-deepfake | |
| - adversarial-audio | |
| - benchmark | |
| # RVCBench Demo | |
| Interactive demo for the [RVCBench](https://github.com/Nanboy-Ronan/RVCBench) benchmark. | |
| Explore how modern voice cloning models can replicate a speaker's voice — and how audio | |
| protection methods disrupt that cloning. | |
| **Paper:** [arXiv:2602.00443](https://arxiv.org/abs/2602.00443) | |
| **Dataset:** [Nanboy/RVCBench](https://huggingface.co/datasets/Nanboy/RVCBench) | |
| **Code:** [Nanboy-Ronan/RVCBench](https://github.com/Nanboy-Ronan/RVCBench) | |