Real-time call intelligence

Stop scams.
Live.

Phigil listens to live voice calls and flags scams, fraud and threats as they are spoken, in roughly 80 milliseconds, inside your own network. National carriers deploy it to shield every subscriber from scams; government agencies use it for real-time voice intelligence.

Built for tier-1 carriers and government agencies, at national scale.

$0T lost to scams worldwide in 2024.
Most of it started with a conversation.

Source: Global Anti-Scam Alliance, Global State of Scams 2024, est. US$1.03 trillion.

How it works

Three steps, on every call, in real time.

  1. 01

    Listen

    Stream call audio into Phigil over your existing stack, whether SIP, WebRTC, or our SDK. No call leaves your network unless you want it to.

  2. 02

    Understand

    Each utterance is transcribed and classified for scam patterns, social-engineering and threats. Roughly 80 ms per segment, CPU-only.

  3. 03

    Act

    Warn the caller, alert an agent, or block the line. Every flag carries a category, confidence score and a plain-language explanation.

Action detection

See the threat as it happens.

Phigil watches camera feeds and recorded video for weapons, fights and other violent actions, and raises an alert in near real time with the moment, the people involved and supporting frames. Your team reviews the evidence and decides what to do.

  • Weapons
  • Fights
  • Near real-time alerts
  • Human review
Real Phigil detections on public-domain film: The Big Combo (1955), Kansas City Confidential (1952).

Capabilities

One trust layer. Several signals.

Flagship 01

Real-time scam & threat detection

Catch impersonation, authorised-push-payment fraud and coercion while the call is still happening. Per-speaker transcripts, category, confidence and an explanation, all streamed live rather than in a nightly batch.

  • ~80 ms per utterance
  • Per-speaker attribution
  • Explainable verdicts
Near real time02

Action detection in video

Spot weapons, fights and other violent actions in camera feeds and recorded video, in near real time. Each alert shows the moment it happened, supporting frames and suggested matches to enrolled people, so your team can respond fast. A person reviews every alert; a face match does not establish responsibility.

  • Near real-time alerts
  • Evidence and timestamps
  • Human review
03

Age assurance

Estimate age from a single image or a live camera frame for onboarding, age-gating and compliance, without storing documents.

04

Identity verification

Match a face against an enrolled reference to confirm a person is who they claim to be, at sign-up or step-up.

05

Delivered with you

One authenticated API into your existing voice stack, rolled out with our telco OSS delivery partner from paid pilot to national scale. Tracing, metrics and support throughout.

Built for scale

Engineered for the people who can't afford a false sense of security.

Runs in your VPC

Deploy on-prem or in your cloud. Voice data stays inside your perimeter. A requirement, not an upsell.

No GPU fleet required

Voice classification uses CPU-only ONNX models, so cost scales with traffic instead of with a rack of accelerators.

Observable by default

OpenTelemetry traces and Prometheus metrics out of the box. You see every decision and every millisecond.

Privacy by design

Live voice is processed in-stream. Video kept for action detection stays only until deletion or the configured retention limit. Tune retention to your policy.

0ms per-utterance verdict
0% in your perimeter
0 signals, one API
CPU no accelerators needed

FAQ

Questions buyers actually ask.

How is Phigil delivered, and is it proven?

We deliver through an established telco OSS/BSS partner with 30 years in the industry, and we're already live in European and African carrier networks. Every engagement is a managed rollout. A short paid pilot first, then national scale. There is no self-service signup.

Who is Phigil for?

Phigil is a national-scale platform, not a point tool. Tier-1 and primary national carriers deploy it across the network to protect every subscriber from scam and fraud calls. Government agencies license it for real-time voice intelligence. Every engagement starts with a short paid pilot.

How does Phigil integrate with our voice stack?

Over the interfaces you already run, whether SIP/RTP, WebRTC or our SDK. Phigil sits in the media path or taps a fork of it, and returns verdicts on a stream you consume from your IVR, agent desktop or fraud engine.

Does our customers' audio leave our network?

Only if you choose to route it that way. Phigil is designed to run inside your VPC or data centre, so voice never crosses your boundary by default.

Is it fast enough for a live call?

Yes. Classification runs in roughly 80 ms per utterance on CPU, which is well within the window to warn a caller or agent mid-conversation.

How do you handle false positives?

Every flag carries a category, a confidence score and a plain-language explanation, and the decision threshold is yours to set, so you tune the trade-off between catching scams and interrupting good calls.

What else can the platform do?

The same authenticated API offers action detection in video, age assurance and identity verification, so one integration covers live-call defence, physical security, onboarding and age-gating.

Real-time intelligence on every call in your network.

Tell us about your network and we'll scope a paid pilot on your own infrastructure, delivered with our telco partner.