Audio — Metis

Overview

Metis is our multibit audio watermarking model. It embeds a 20-bit payload into the signal — a structured tag you get back on decode.

Use Metis when you need to know which piece of content this is. Typical use cases:

1. Per-file or per-session IDs
2. Distribution tracking and leak tracing
3. Creator / licensee attribution
4. Any workflow where a yes/no answer isn't enough and you need to recover a specific tag

Imperceptibility

The watermark sits below the perceptual threshold. In a blind A/B test, listeners cannot reliably distinguish the watermarked signal from the original.

Listen for yourself

Select an example to compare the original audio with its Metis-watermarked version:

Spectrograms

Side-by-side spectrograms of the same clip. The watermarked plot is visually near-identical to the original, demonstrating how little energy is added.

100%

Format & Configuration

Robustness

The 20-bit payload is designed to survive the real-world transformations audio typically goes through once it leaves your pipeline.

Supported attack classes

Background music mixing

A music track is mixed into the watermarked signal at a realistic SNR. This is the common "posted over a backing track" scenario.

Gaussian noise

White noise added at 20 dB SNR — simulates microphone hiss, noisy transmission, or deliberate masking attempts.

Cuts / splicing

A short segment is removed from the middle of the clip and the two halves are rejoined — simulates edits, ad breaks, or clip re-use.