Enterprise-grade, real-time deepfake detection API for face, image, video and audio.
One API call checks liveness, face swaps, AI-generated faces and unsafe content before your onboarding flow trusts a selfie.
- Liveness check
- Face swap check
- Identity overlay check
- AI deepfake check
- AI content check
- NSFW check
Built for eKYC and onboarding
Designed for identity verification companies.
- eKYC providers
- Banks and fintech onboarding
- Identity verification platforms
- Lending and insurance onboarding
Fits your existing selfie step
Send the selfie or video you already capture. No new step for your user.
Catches what liveness misses
Face swaps, identity overlays, AI-generated faces and unsafe content in the same call.
One score for your policy
A unified risk score with signal-level evidence. Your policy makes the final call.
One API · Multiple signals
Beyond liveness.
A liveness check only asks whether a live person is present. NeuroVerify checks six signals in a single API call and returns one unified score with the evidence behind it.
- Live Presence AuthenticityIs a real, live person in front of the camera?
- Face Composite AnalysisHas the face been swapped or blended?
- Identity Overlay DetectionIs another identity layered over the face?
- Generative Media AnalysisWas the face generated or altered by AI?
- AI Content ComplianceDoes AI-generated content break your policy?
- Visual Safety ScreeningIs the image unsafe or NSFW?
How NeuroVerify works
From API key to verdict in four steps.
Get your API key
Provision a scoped credential for the application, service, or approved agent.
Add the SDK or REST call
Connect through a native mobile SDK, a backend SDK, REST, or bounded MCP tools.
Send face, video or audio
Submit authorized media from your capture flow for analysis.
Get one score and signals
Receive risk, status, and signal fields for the policy that controls the decision.
SDK-first integration
One API.
Every stack.
Native SDKs for Android, iOS and Flutter, plus Python, TypeScript, Go and Java for your backend. Send the selfie, get the verdict.
Sign in for API access$ npm install @neuraldefend/sdk
import { NeuroVerifyClient } from "@neuraldefend/sdk"
const result = await new NeuroVerifyClient().detectImage("selfie.jpg")Mobile SDKs
Native capture apps- KAndroid (Kotlin)
- SiOS (Swift)
- FFlutter
Backend SDKs
Server-side checks- PyPython
- TSTypeScript / Node.js
- GoGo
- JJava
REST API
For everything elseAlready have capture? Send the image to POST /detect/image and get every signal back in one JSON response.
AI agents
MCP serverGive approved AI assistants bounded image and video authenticity tools, with API keys kept outside prompts.
Two lines to integrate<200 ms p95Live in under 24 hours
Deployment options
Run it where your data must stay.
Managed cloud API
Fastest path to production. Neural Defend runs the service.
Best for: Speed to productionPrivate cloud / VPC
A dedicated deployment in your network and chosen region.
Best for: Regulated, high volumeSecure container
A portable runtime inside your approved environment.
Best for: Portable private setupsOn-premises
Runs inside your own data-centre infrastructure.
Best for: Strict local processingAir-gapped
Fully isolated, with no external network path.
Best for: Sensitive environmentsDesigned for real-world variation
Evaluated across real capture conditions.
NeuroVerify does not infer a person's ethnicity or nationality. Validation scope and methodology are available during evaluation.
Knowledge centre
Learn more about deepfakes in onboarding.
Start with NeuroVerify