
Free / Open-sourcePoint, shoot, and get an AI read on whether someone is lying
Free / Open-sourcePoint, shoot, and get an AI read on whether someone is lying

AI lie detection and heart-rate analysis for video conversations
Estimated monthly website visits
Similarweb estimates for this domain, not active users. Only available observation months are shown; collection date is separate from the traffic period.
Collected Nov 11, 2026

This is our editors' assessment out of 5, not an average of user ratings. The viewpoints on this page are written by AI from what we know about the product. They are not customer reviews.
According to OpenAITools.app telemetry verified on 2026-11-11, LiarLiar.ai (liarliar.ai) is an AI platform indexed under AI Detector generating 1.05K monthly visits with a month-over-month traffic delta of -1.8K (-63.2%). Its primary geographic market is United States (100% traffic share), and it operates on a Paid pricing model. Top competing alternatives by monthly volume include Liars.AI (0 visits/mo), Verificient (66.12K visits/mo), PolygrAI (2.01K visits/mo).
Wild concept tracking heart rates over video feeds, accuracy feels hit or miss.
Hard to tell if it actually works or just guesses.
Cool tech demonstration for micro-expressions.
Needs good lighting to function properly.
AI-synthesized perspectives grounded in live site inspection, pricing structure, and category benchmarks — presented as editorial viewpoints rather than individual customer testimonials.
Estimates heart-rate variation from imperceptible colour changes in the face captured by the camera, using remote photoplethysmography.
Tracks involuntary facial expressions, eye movement, posture and gesture to flag non-verbal cues commonly associated with stress or concealment.
Watches for swings in pitch, tone and speaking speed, and for changes in word choice that may indicate discomfort with what is being said.
Transcribes the conversation as it happens and delivers a running truthfulness estimate alongside the transcript.
Every session can be recorded and saved locally, ending with a detailed report covering heart rate, body language and the other analysed channels.
LiarLiar.ai is a Windows and Mac desktop application built around the idea that several small, easily missed signals add up to a useful picture of how candid a speaker is being. Rather than relying on a single indicator, it reads the video feed on multiple channels at once: heart rate inferred from tiny colour changes in the face, involuntary facial micro-expressions, shifts in posture and gesture, and variations in pitch, tone and pace of speech. A language layer also watches for changes in word choice that people often make unconsciously under pressure.
The core technique is remote photoplethysmography (rPPG). Blood volume under the skin changes with every heartbeat, subtly altering facial colour in a way the human eye cannot catch but computer-vision algorithms can. From that signal the tool derives heart-rate variation, which it combines with the other cues and a psychological interpretation layer to produce an easily read truthfulness estimate. The analysis runs live during a call, so you see the reading develop as the conversation unfolds.
The tool works on almost any video source, including Zoom, Google Meet, Microsoft Teams, Skype, YouTube videos and local files. Sessions can be recorded and are saved to a folder on your own machine, and each one ends with a report you can revisit later. The developers state plainly that no lie-detection tool is 100% accurate, and that recording or analysing someone without their consent is illegal in many places. The company has rebranded the product as PolygrAI and points users to the newer site.
Review recorded or live interviews with an extra analytical layer that highlights moments where body language and heart-rate signals shifted.
Add a second set of observations to video interviews, provided every participant has given informed consent.
Run YouTube videos or local clips through the analyser to study delivery, stress signals and non-verbal communication.
Give clients a neutral readout of how they present under pressure, so they can work on presence, pacing and honesty in delivery.
Side-by-side telemetry comparison of competing AI tools in the same primary category
| Rank | AI Tool | Monthly Visits | MoM Growth | Direct traffic share | Pricing | Head-to-Head |
|---|---|---|---|---|---|---|
| ● | LiarLiar.ai | 1.05K | -63.2% | 39% direct | Paid | Current |
| 1 | Liars.AI | 0 | 0% | — | Free Trial, Paid | vs Liars.AI |
| 2 | Verificient | 66.12K | -5.2% | 61% direct | Contact for Pricing | vs Verificient |
| 3 | PolygrAI | 2.01K | -46% | 39% direct | Freemium | vs PolygrAI |
| 4 | Facia | 60.13K | -21.6% | 45% direct | Contact for Pricing | vs Facia |
| 5 | Face Age AI | 40.73K | +36.5% | 40% direct | Free | vs Face Age AI |
| 6 | AI Detector for PPT | 26.82K | -38.6% | 15% direct | Free Trial, Paid | vs AI Detector for PPT |

Free / Open-sourcePoint, shoot, and get an AI read on whether someone is lying
Free / Open-sourcePoint, shoot, and get an AI read on whether someone is lying

Biometric identity verification and AI-powered remote exam proctoring
Biometric identity verification and AI-powered remote exam proctoring

Free / Open-sourceAI interview platform that scores, profiles and flags potential deception
Free / Open-sourceAI interview platform that scores, profiles and flags potential deception

Liveness and deepfake detection for identity verification
Free / Open-sourceFree AI age detector that estimates how old you look from a single selfie
Free / Open-sourceFree AI age detector that estimates how old you look from a single selfie
Free / Open-sourceDetect AI-written slides in any PowerPoint deck
Free / Open-sourceDetect AI-written slides in any PowerPoint deck

See your enterprise the way attackers do — observe, understand, signal, and respond at AI speed
See your enterprise the way attackers do — observe, understand, signal, and respond at AI speed
Free / Open-sourceAI detector that highlights evidence, not just a score
Free / Open-sourceAI detector that highlights evidence, not just a score

Free / Open-sourceMultimodal emotion recognition across video, audio, image, and text
Free / Open-sourceMultimodal emotion recognition across video, audio, image, and text
Free / Open-sourceDetect, humanize and verify AI content in one place
Free / Open-sourceDetect, humanize and verify AI content in one place

Free / Open-sourceTwo minutes, one stranger, one question: human or AI?
Free / Open-sourceTwo minutes, one stranger, one question: human or AI?
Free / Open-sourceAI image and deepfake forensics that shows its work
Free / Open-sourceAI image and deepfake forensics that shows its work