Detect AI voice fraud
on live calls.

Synthetic voices are now indistinguishable from real ones.
PulmoForge identifies them — live, during virtual meetings.

Explore the Platform → Run Demo
680%
rise in voice deepfakes year-over-year in 2024
Pindrop Voice Intelligence & Security Report, 2025
$40B
projected AI fraud losses globally by 2027
Deloitte Center for Financial Services, 2024
1,300%
increase in deepfake fraud attacks on enterprises in 2024
Entrust Cybersecurity Institute, 2024
1 in 10
adults globally have encountered an AI voice scam
SQ Magazine, 2026
Threat landscape
Your meetings are
the new target.

Impostors can slip into everyday virtual conversations — stealing data, misleading teams, and leaving organizations exposed. Continuous participant verification, built to catch synthetic voices as they speak, stops the threat before it spreads.

Enterprise fraud tools cover phone systems and contact centers. PulmoForge is focused on the gap they don't: live video meetings, where codec compression hides what older detectors look for.

The cost of inaction
$25M
Lost in a single deepfake call
A Hong Kong finance worker transferred $25M after a deepfake video call impersonated their CFO — 2024.
11s
To clone any voice
Modern AI needs just 11 seconds of audio to produce a convincing voice clone — available to anyone with a standard device.
$500k
Average enterprise incident cost
Average financial loss per deepfake voice fraud incident reported by enterprise security teams.
AI voice fraud — growth trend
↑ Rapid growth
Low High 2022 2023 2024 2025 Peak
Where fraud is hitting hardest Pindrop, 2025
01
Deepfakes in live meetings
Impostors in virtual meetings — stealing data and misleading teams in real time.
02
Contact center deepfakes
AI-generated voices bypassing agent verification within seconds of connection.
03
Threat monitoring gaps
False positives and missed detections cost enterprises millions annually.
How it works
Simple. Fast. Built for real calls.
01
Someone joins your call
Could be a real person. Could be an AI-generated voice cloned from a CEO, a colleague, or a family member. They sound identical.
02
PulmoForge listens
Audio is scored in real time — looking for residual artifacts synthetic voices leave behind, even after Zoom's Opus compression.
03
You get a risk score
A continuous probability score tells you how likely the voice is AI-generated. PulmoForge supports human judgment — it doesn't replace it.
Competitive positioning
How we compare to other detectors.
SystemMeeting audioCompression trainedStatus
PulmoForge✓ Zoom + Opus✓ YesEarly Access
Legacy detectors✗ Lab audio only✗ RarelyBypassed by modern gen AI
Enterprise fraud tools✓ Phone systemsUnknownClosed platforms

Most voice fraud systems were not built around Zoom compression pipelines. PulmoForge was trained directly on compressed meeting audio.

Technical capabilities
What the system does.
Codec resistance
Codec-resistant detection
Trained on Zoom's Opus 32kbps compression pipeline. Detects synthesis artifacts that survive real-world codec degradation — where most detectors fail.
False positive rate
Low false positive rate
Designed to minimize false accusations on genuine voices. Results are probabilistic — intended to assist, not replace, human review.
Architecture
WavLM backbone
Fine-tuned on large-scale speech data. Attention pooling isolates subtle synthesis artifacts across codec-compressed audio with high precision.
Inference mode
Live call monitoring
Per-second risk scoring on real-time calls and meetings, with continuous probability output designed for human review workflows.
Data handling
Audio is not stored or retained
Detection runs on a per-second scoring basis. No audio recordings are saved, logged, or transmitted beyond the detection pipeline.
Contact
contact@pulmoforge.com
For enterprise inquiries, compliance questions, or security disclosures. We respond to all messages within 2 business days.
Legal
Detection only — not a guarantee
PulmoForge is a probabilistic detection tool. Results are advisory. Full terms and privacy policy available at the links below.
Early access
Be first when we launch.

Free beta access goes to the waitlist first — no spam, just a single email when it's ready.

Join Waitlist → Run Demo