Exiphore vs Sensity AI
Exiphore
exiphore.comSensity AI
sensity.aiSide by side
| Figure | Exiphore | Sensity AI |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | Yes |
| Open source | — | — |
| Web | — | Yes |
| Windows | — | Yes |
| API | — | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 0 |
| Spec score · AI Deepfake Detection Tools | 7.4 (#14) | 7.6 (#12) |
| Company | The about page names Sonu Kumar as founder and AI lead but does not state a founding year or headquarters. | Sensity B.V. is based in Amsterdam, Netherlands, and its about page says the company was born in late 2018. |
| Deployment | The platform is installed on customer infrastructure, supports air-gapped and private-cloud deployment, and requires no specialised accelerators on standard server hardware. | Sensity offers cloud and on-premise deployment, including server, workstation, and USB dongle configurations. |
| Integrations | The opened maker pages describe no named third-party integrations and state that there is no external API dependency in the examination path. | Sensity offers a Microsoft Teams app that analyzes meeting participants’ live audio and video for signs of deepfake manipulation. |
| Intended users | The maker identifies law-enforcement and security agencies, police units, forensic science laboratories, prosecution, financial crime and intelligence teams as intended users. | Sensity describes its intended users as states, organizations, businesses, and individuals seeking protection from malicious deepfakes. |
| Reports | Each exhibit can receive a finding, evidence breakdown, confidence interval, quality ceiling, custody record, examiner adjudication and digest-sealed PDF report. | The platform says it provides reproducible, explainable, traceable forensic reports intended to support court use. |
In their own words
Exiphore
Exiphore is a self-hosted forensic media authentication platform for examining video, images, audio, documents and text for signs of synthetic generation or manipulation. It combines eight independent families of forensic evidence and pools related measurements so related signals are not counted twice. Each exhibit can receive a finding, evidence breakdown, confidence interval, quality ceiling, custody record, examiner adjudication and a digest-sealed PDF report. Ambiguous evidence can produce an inconclusive result. A qualified, named examiner must review measurements and sign before release as an expert opinion. Exhibits may be submitted singly, in batches, by URL or from a monitored path, and fingerprints can link across cases as investigative leads. Installation runs on customer infrastructure, including air-gapped and private-cloud environments, without specialised accelerators on standard servers. Evidence remains in a content-addressed, write-once locker with re-verified seals and hash-chained custody records. Pricing is on request, with access by demo request.
Sensity AI
Sensity AI analyzes images, video and audio for manipulated faces, AI-generated media, synthetic voices, voice cloning and file tampering. Its multilayer assessment examines visual artifacts, acoustic patterns, metadata, behavioral cues and inconsistencies across media types. Users can submit files or URLs through the web platform, analyze multiple items and track results in a dashboard. The REST API accepts image, video or audio by direct upload or public URL and returns an assessment. Direct uploads are limited to 500 MB, and signed upload URLs expire after one hour. Teams can use member roles; deployment options include cloud and on-premise configurations for servers, workstations or USB dongles. KYC workflows can use an SDK and API, and the enterprise offering describes Microsoft Teams video-call analysis. The Teams app captures 30 seconds of audio and video per analysis, and audio results require speech during that window. Sensity describes its forensic reports as reproducible, explainable and traceable for court support. It offers a trial, but pricing is on request and there is no free plan listed.