Free online WebRTC leak test. Detect IP address leaks through your browser even while using a VPN. Checks IPv4, IPv6, mDNS and STUN. Fast, instant, private.
Click Start scan to see what IP addresses your browser exposes via WebRTC.
WebRTC can leak your real local and public IP addresses to websites even when you are using a VPN. Click Start scan to detect what your browser exposes.
Public IP-
The IP address websites see. With a VPN on this should match your VPN server, not your ISP.
Local IPs-
Your private network address (192.168.x, 10.x). Modern Chrome hides this behind an mDNS hash ending in .local.
IPv6-
Your IPv6 address. If your VPN does not tunnel IPv6, this leaks even when IPv4 is protected.
Status-
How to fix a WebRTC leak
If your real public IP appeared above while you had a VPN active, your VPN is leaking. Pick the section for your browser and follow the steps.
Chrome and Edge
Chrome has no built-in WebRTC toggle. Install the official "WebRTC Network Limiter" extension from the Chrome Web Store (made by Google) and set it to "Use default public and private interfaces." Or switch to a VPN with built-in WebRTC leak blocking (Mullvad, ProtonVPN, NordVPN, ExpressVPN all advertise it).
Firefox
Type about:config in the address bar and accept the warning. Search for media.peerconnection.enabled and double-click to set it to false. This disables WebRTC entirely - video calls in Google Meet, WhatsApp Web, and Discord browser will stop working until you turn it back on.
Brave
Paste brave://settings/privacy into the address bar, scroll to "WebRTC IP handling policy," and change it to "Disable Non-Proxied UDP." Brave is the only major browser with this option in the UI, no extension required.
Safari (macOS / iOS)
On macOS: Safari > Settings > Advanced > Show features for web developers > Feature Flags > disable WebRTC Platform UDP Sockets. On iOS: Settings > Safari > Advanced > Experimental Features > toggle WebRTC mDNS ICE candidates on.
Best long-term fix: a VPN that blocks WebRTC at the app level
If you need video calls to keep working, do not disable WebRTC - switch to a VPN that routes WebRTC traffic through the tunnel or blocks it at the OS level. Mullvad, ProtonVPN, NordVPN, and ExpressVPN all do this correctly. Many cheap and free VPNs do not.
Seeing a .local address? That is not a leak
Chrome replaces your real local IP with a hashed mDNS string like a1b2c3d4.local. This is a privacy feature added in Chrome 76 (2019) - the hash cannot be tracked back to your real network and does not help fingerprinting.
Was this tool helpful?Rate WebRTC Leak Test:5.0(1 rating)Thanks for rating!
WebRTC Leak Test is a free, browser-based online utility that lets you detect IP address leaks through your browser even when using a VPN.
Cost: Free, no signup
Install: None — runs in the browser
Privacy: Runs locally, no uploads
Platforms: Windows, macOS, Linux, Android, iOS
Time: Under a minute
WebRTC Leak Test: Understand Browser IP Candidates
This WebRTC leak test shows the network candidates your browser exposes during a connection check. Compare the displayed result with and without your normal VPN setup to see whether the visible addresses change. A public address, private address or masked .local candidate needs context: this browser test cannot certify that every application or network path is protected.
This tool gathers the connection candidates exposed to the page and can contact STUN servers during the check. The result describes this browser session. It is not a local-only network operation and does not establish how every application uses your VPN.
How to Read Your Result
Public address — compare a public candidate with the address and routing you expect for the current connection. Split tunnelling, browser policy and VPN configuration need context; an address by itself does not identify the reason it appeared.
Local candidates — private addresses or privacy-masked .local names can appear depending on browser and network policy. A masked name is not the same as a directly displayed public address.
IPv6 — check the candidate type and your expected IPv6 routing as well as IPv4. The browser result is not a complete audit of VPN or network configuration.
Why WebRTC Leaks Even With a VPN On
VPN routing, split-tunnel settings, proxy configuration and browser candidate policies affect the addresses that are exposed. Read the current documentation for your exact setup and compare repeat runs with the same browser. A brand name or price does not guarantee a particular WebRTC result.
If the displayed candidates differ from what you expect, check the VPN and browser documentation before changing settings. Restricting or disabling WebRTC can affect browser calls and other real-time features, so verify the intended apps after any change.
Per-Browser Fix Summary
Chrome / Edge — review the current browser and VPN guidance for candidate-routing controls. A third-party extension is not automatically necessary or sufficient.
Firefox — review current privacy and connection settings and understand which call features a change affects.
Brave — inspect the current WebRTC IP-handling policy and compare the result after one documented change.
Safari — check the current version’s supported controls rather than relying on an experimental flag name from a different release.
Any browser — confirm the expected network path and test the apps you need. No single setting change guarantees privacy for every application.
Seeing a .local Address? That Is Not a Leak
A .local ICE candidate is a browser privacy mechanism that can hide a directly displayed local address. Interpret it alongside the other candidates and the expected network path. Its presence alone does not prove either a public-IP leak or complete privacy.
Common Myths Worth Busting
Private-browsing mode does not by itself establish how WebRTC candidates are routed. Test the actual mode and connection you intend to use.
A VPN label does not show every routing and browser-policy setting. Compare the observed candidates with the expected connection.
Disabling WebRTC is not a universal requirement. Understand the current setup and the effect on calling features before changing it.
A .local candidate is not a directly displayed public IP. It is also not proof that every other network path is protected.
Read the Full Guide
For a deeper walkthrough with screenshots, a fix video, and browser-by-browser troubleshooting, see our full article: What Is a WebRTC Leak and How to Fix It.
Related Tools
Latency Checker — separate keyboard and mouse event-timing tool
Webcam Test — uses the same getUserMedia/WebRTC APIs
The browser may restrict candidate gathering, a STUN request may fail or the network may block the check. Incomplete output is not proof that there is no leak and is not proof that a VPN has failed.
Is a .local address the same as a leaked public IP?
No. A .local candidate can be a privacy-masked local identifier. Read the candidate type and compare public addresses with your expected connection; the label alone does not establish a public-IP leak.
Does a no-leak result guarantee my VPN privacy?
No. This checks browser-visible WebRTC behavior under the current conditions. Other applications, DNS handling and different network routes are separate questions, so it should not be treated as a complete VPN security audit.
Monitor internet stability for gaming and video calls. Track request failures, latency spikes and delay variation with a live graph and downloadable results.
01 / 10DDR5 buying mathPay $120 more for 2 nanoseconds?CL30 vs CL36 looks big on the box. The real difference is 2 nanoseconds.02 / 10What CL really isCAS latency counts cycles, not timeCL is how many clock ticks the RAM waits before answering. Ticks get faster with speed.03 / 10The one-line formulans = 2000 x CL / MT/sTrue latency in nanoseconds. DDR5-6000 CL30: 2000 x 30 / 6000 = 10.0 ns.04 / 10CL30 vs CL36 at 600010.0 ns versus 12.0 nsSame speed, different CL: the whole debate is about 2 nanoseconds of wait time.05 / 10The tie surprise7200 CL36 is also 10.0 nsSo is 6400 CL32. A higher CL on a faster kit can match a lower CL exactly.06 / 10What 2 ns buys in gamesRoughly 1-4% average FPSOnly when CPU-bound, and benchmarks disagree. Smoother 1% lows are the steadier win.07 / 10Price check, Aug 11, 2026The CL30 premium: $120G.Skill CL30 $599.99 vs CL36 $479.99. A Patriot CL30 kit: $429.99. Shop across brands.08 / 10The EXPO/XMP gotchaYour CL30 may be running CL40Kits boot at JEDEC defaults until you enable EXPO or XMP in BIOS. Check yours today.09 / 10The X3D exceptionBig cache blunts CLOn 7800X3D-class CPUs, the stacked cache blunts CL gains. Buy CL36 and save.10 / 10The verdictSmall delta: yes. Upgrade: no.Compare your two kits in real nanoseconds - presets loaded, math done for you.
01 / 10Phone vibration testYour phone stopped buzzingBefore you book a repair, find out whether it is the motor or just a setting.02 / 10The symptomMissed calls and silent alertsA dead motor is easy to miss. You only notice the calls you never felt arrive.03 / 10What is insideA tiny weight on a motorMost phones spin an offset weight or drive a linear actuator to make the buzz.04 / 10Check this firstSettings fake a dead motorSilent mode, Do Not Disturb and per-app vibration all switch the buzz off.05 / 10Run the testOne tap, three patternsThe browser asks the phone to vibrate in short, long and pulsed patterns.06 / 10Result: weakYou feel it, but barelyA faint buzz often means a loose motor mount or a case damping the vibration.07 / 10Result: nothingNo buzz on any patternWith settings ruled out, silence points at the motor or its connector.08 / 10Result: on and offIt works, then it does notIntermittent buzzing usually means a failing solder joint or a worn motor.09 / 10One honest limitiPhones cannot run this testSafari on iOS does not support the browser vibration API, so use Android.10 / 10Your turnFind out in thirty secondsRun the three patterns, then decide whether it is a setting or the hardware.