TruthHound
One scan · £14.99 · No subscription

Is the person you're
talking to real?

Get an evidence-backed scan of their photos, messages, and voice notes in under 60 seconds. No subscription. £14.99 once.

End-to-end encrypted · Private by design · GDPR-compliant
Analysis · TH-4821
2.4s
Indicators
12checked · 7 triggered
Findings
AI-generated face markers
Image
Inconsistent lighting between photos
Image
Generic bio phrasing detected
Profile
Urgency & financial pressure
Chat
NextRecommended next step: request a live video call.
CONFIDENCE · 94%
Sample report
7 warning signs detected
— The three-question test

Three questions you can't answer alone.

Are their photos AI-generated?

We check for diffusion artefacts, face-swap signatures, and geometry inconsistencies across every photo you upload.

Do their messages match a known scam script?

We pattern-match against thousands of romance and investment scam templates, and flag urgency, love bombing, and financial pressure.

Is the voice note actually them?

We scan voice notes for cloned-speech signatures and synthetic patterns common to ElevenLabs, Play.ht, and similar tools.

— How it works

Three steps. One quiet verdict.

01

Upload

Add screenshots, photos, voice notes, or messages — securely and privately.

02

Analyze

TruthHound scans patterns, inconsistencies, and behavioural signals across the upload.

03

Decide

Receive a confidence score and a clear report before you trust.

— What you'll see

A real report, on a real (fictional) profile.

Analysis · TH-48212
Generated 14 March 2026

Marcus, 34

Source: Hinge profile · 11 messages · 3 photos

Indicators
12 checked
Triggered
7
Confidence
94%

Photo authenticity

3 analysed · 2 flagged

Inconsistent earring geometry

High

Detected — Earring shape and position differ between photos 2 and 3, despite same outfit and lighting context.

Why it matters — Geometry inconsistencies across photos of the same person are a common signature of AI face generation or face-swapping.

Diffusion-model background artefacts

Moderate

Detected — Background blur in photo 1 shows smearing patterns typical of diffusion-model generation rather than optical depth-of-field.

Why it matters — Real cameras blur backgrounds with smooth optical falloff. Diffusion smearing suggests the photo was generated, not taken.

Photo 3 — no manipulation markers

Low

Detected — No detectable AI-generation or splice indicators in photo 3.

Why it matters — One clean photo isn't proof of identity, but it raises the value of insisting on a live video.

Profile consistency

2 flags

Generic scam-script bio phrasing

High

Detected — Bio uses generic phrasing matching 14 known scam-script templates (e.g. "looking for someone real in a fake world", "lost my partner two years ago").

Why it matters — Bios that pattern-match known scam scripts are reused across many fake profiles, often by the same operator.

Stated job title not corroborated

Moderate

Detected — Stated job title ("Offshore engineer, Aberdeen") is not present in any LinkedIn footprint for the named person.

Why it matters — Roles like offshore engineer, military deployed, or oil-rig contractor are commonly used to explain away the inability to meet or video call.

Behaviour signals

3 flags

Push to move off-platform

High

Detected — Urgency around moving the conversation to WhatsApp within 48 hours of matching.

Why it matters — Scammers move off-platform quickly to escape moderation and screenshot review by the dating app.

Financial topic introduced early

Moderate

Detected — Financial topic (a stuck wire transfer, mention of crypto investing) introduced on day 4.

Why it matters — Genuine connections rarely surface money in the first week. Early financial framing is a precursor to the ask.

Refused live video on three occasions

High

Detected — Live video declined three times with shifting reasons ("bad signal offshore", "camera broken", "company policy").

Why it matters — Pattern refusal of video is the single strongest behavioural indicator of catfishing in our dataset.

Voice

No data
No voice notes provided. Add a voice note to your scan to enable voice-cloning detection.

This is a real TruthHound report. Yours will look exactly like this — for a real person, in 60 seconds.

— Pricing

One scan. One price.

Single Verdict
£14.99one-off
Charged in your local currency at checkout.
  • 12-indicator analysis across photos, messages, voice notes
  • Full evidence-backed report
  • Downloadable PDF evidence pack
  • Confidence score + recommended next step
  • Re-run with new evidence within 7 days

No subscription. No auto-renewal. Pay once, get your report.

— FAQ

Questions, answered.

— Honest limits

TruthHound surfaces signals — it's a second opinion, not a verdict. AI detection is probabilistic and may produce false positives or false negatives. We give you the evidence; the judgement is still yours. If you're in immediate danger, contact your local emergency services.

Stop wondering.
Find out.

One scan. £14.99. A clear, evidence-backed report in under 60 seconds.