// Real GibberLink Protocol  ·  ggwave Engine  ·  100% Offline  ·  No Files Needed

GIBBERLINK

The actual data-over-sound protocol that went viral when two AI agents detected each other and switched mid-conversation. Encode English into FSK audio. Decode it back. Works over any speaker and mic.

FSK Modulation Reed-Solomon ECC Air-Gap Compatible Fully Offline Zero Dependencies
01

// English → GibberLink Sound

Encode to Audio

TRANSMIT TERMINAL
0 / 140Max 140 chars · Reed-Solomon ECC applied automatically
02

// GibberLink Sound → English

Decode from Audio

RECEIVER TERMINAL

Drop a .wav here, or

Accepts .wav files containing GibberLink audio

Point your mic at a GibberLink audio source. Decoding is automatic — the result appears the moment a valid transmission is detected.

03

// Protocol Details

How It Works

FSK Modulation

Multi-frequency Frequency-Shift Keying. 3 bytes transmitted simultaneously via 6 tones across a 4.5 kHz band split into 96 frequencies. dF = 46.875 Hz per step.

Reed-Solomon ECC

Built-in error correction recovers data from noisy or partially clipped audio. Tolerates real-world interference, background noise, and distance.

Air-Gap Compatible

No network required. Works between completely isolated devices using only speakers and microphones. Ideal for offline pairing and IoT provisioning.

Up to 16 bytes/sec

Audible Fast: ~16 bytes/sec. Ultrasound modes run at 15–19.5 kHz — inaudible to most humans, but still captured by nearby microphones.

The Viral Moment

Built by Boris Starkov and Anton Pidkuiko. Won first place at the ElevenLabs Worldwide Hackathon in 2025. Two AI agents switched mid-conversation — 15M+ views on X.

Powered by ggwave

This page uses the real ggwave engine by Georgi Gerganov — compiled to WebAssembly and fully embedded. No external files, no server, works offline. MIT licensed.