VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

Step 1: Upload an audio file or select one from the provided samples, choose a watermark, and generate the watermarked audio.

Step 2: Download the generated watermarked audio, then use Zero-Shot Voice Cloning tools to generate the cloned audio. Some available tools are:

• CosyVoice2: Scalable Streaming Speech Synthesis with Large Language Models
• F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
• MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

Step 3: Upload the cloned audio and decode your watermark.