TruthLens

The free, open-source AI detector browser extension that flags ChatGPT-generated text, deepfake images, and cloned voices in real time — 100% on-device, zero telemetry.

⭐ Star on GitHub Install in 30 seconds
MIT License Manifest V3 Zero telemetry PRs welcome

What TruthLens detects

🧠 AI text (ChatGPT, GPT-4, Claude, Gemini)

Burstiness, common-word ratio, 25+ LLM phrase fingerprints, syntactic uniformity.

🖼 Deepfake images

Midjourney, DALL·E, Stable Diffusion, Leonardo, Ideogram, Flux. Pixel-level pluggable heuristics.

🎙 Cloned & synthetic voices

Spectral flatness, silence regularity, pitch jitter on any <audio> or <video>.

🔒 100% on-device

Nothing leaves your browser. No accounts. No tracking. Audit the source.

🏷 Inline badges

Click any flag to see the underlying signals — transparent, not a black box.

⌨ Hotkey + right-click

Ctrl+Shift+T to rescan. Right-click any image to triage instantly.

Who uses TruthLens?

Install in 30 seconds

git clone https://github.com/mrtomdev/truthlens.git
# Open chrome://extensions → Developer mode → Load unpacked → pick the folder

FAQ

Is TruthLens free?

Yes — MIT-licensed, free forever. No subscription, no trial.

Does it send my data anywhere?

No. Every detection runs in your browser. Open the network tab and confirm.

How accurate is it?

It's a transparent triage tool, not forensic proof. Every verdict shows the underlying signals so you can audit it yourself.

What does it support?

Detects output from ChatGPT, GPT-4, Claude, Gemini, Midjourney, DALL·E, Stable Diffusion, Leonardo, Ideogram, Flux, and synthetic-voice generators.