VIDIZMO integration brief · ONVIF · vidizmo.ai/integrations/catalog/onvif

Integrations / ONVIF

ONVIF

Bring ONVIF cameras and recorders into live analytics over RTSP. Visit website

ONVIF is the open standard for interoperability between IP cameras, recorders and video management software.

The platform reads an ONVIF camera or recorder through the live stream it publishes over RTSP, added by its address, so cameras from different manufacturers join one estate while camera control stays with the existing VMS.

Live Analytics Across a Mixed Camera Estate, Cameras Left in Place

Open as a two-page brief

ONVIF is the open standard for interoperability between IP cameras, recorders and video management software, and it is what makes an estate of cameras from different manufacturers workable. AI Live Insight connects to ONVIF cameras and recorders through the live stream they publish over RTSP, whether that comes from the camera itself or from a recorder that republishes it, and adds live detection to it. The cameras, the recorders and any VMS already running stay as they are.

ONVIF cameras, VMS or NVR, existing estate RTSP / ONVIF live stream AI Live Insight detect, alert, zone rules watchlists, event clips live view, built-in NVR event clips and detections Nexus the record: storage, retention, audited access, hash and chain of custody ask across it AI Intelligence Hub ask, describe, correlate workflows and alerts redact before release Redactor faces, plates, audio, documents; audit trail ONVIF VIDIZMO

How it connects

ONVIF endpoints are supported as stream sources, and the video itself arrives inbound over RTSP. A camera is added in the portal by its address, port and stream path, plus a username and password where the camera requires them, rather than found by network discovery. The platform connects to that endpoint as it would to any camera. No integration with a VMS product is involved.

Encoding stays where it is. AI Live Insight reads the existing H.264 or H.265 stream as the camera emits it, with the codec detected per source, so cameras from different manufacturers run in one service. Detections made on a stream become timed data paired with each recorded segment. Recordings land in the library under one Recording Folder organized by camera, with the same access control, retention and chain of custody as every other content type.

Configuration lives in the portal and is set per camera rather than per folder. The connection is to the stream, and nothing flows back to the camera. Camera control and device management stay with the existing VMS or NVR, as do the VMS's own metadata and user accounts.

What you can do together

01

Analytics on hardware already installed

AI Live Insight reads streams from any camera, NVR or VMS that publishes its video over RTSP, ONVIF devices included, so no camera has to be replaced.

02

One service for a mixed fleet

AI Live Insight runs H.264 and H.265 sources side by side and records each bitstream bit-exact, with no re-encode and no GPU encoder load.

03

Cameras reached through their recorder

Where an NVR or VMS republishes camera streams, AI Live Insight connects to that endpoint as it would to a camera, without a VMS-specific integration.

04

Recordings kept as governed content

AI Live Insight files each camera's recordings in the library with detections paired to every segment, under access control, retention and chain of custody.

A scenario

  1. Monday morningThe campus security IT lead adds the library building's cameras to AI Live Insight, entering each one's address, port, stream path and credentials. A live tile appears for each on the Camera Streams page.
  2. The older buildingsShe adds the NVR's republished endpoints the same way. AI Live Insight treats each as a camera, and the NVR keeps recording exactly as before.
  3. OrganizingShe groups the cameras into folders by building and sets the Camera Streams page to six tiles per row for the control room screen.
  4. The parking structureShe sets detection on each of its six cameras individually, because each camera carries its own settings.
  5. Two weeks laterAn investigator opens a parking structure recording in the library. AI Live Insight's detections sit alongside the segment as timed data, under the same access control and chain of custody as the rest of the library.

What stays where

The cameras and recorders stay in place

AI Live Insight reads the stream a camera, NVR or VMS already publishes. Existing hardware stays installed, encoding stays on the camera, and an existing VMS keeps running.

Control stays with the existing system

Camera control, including pan, tilt and zoom, device management, VMS metadata and VMS user management are not part of the connection. Nothing is written back to a camera or a recorder.

Recordings land in the library

Recordings and their detections carry access control, retention and chain of custody. Where no VMS is in place, the platform records and plays back the live streams itself.

Processing on your own servers

AI Live Insight deploys on premises, including air-gapped sites, so live analysis runs on the customer's own infrastructure.

Products and solutions

Next step

See it on your own ONVIF instance. We will show the connection made, the data moving and the output, then size it for your deployment.

Request a demonstration  or write to sales@vidizmo.ai

sales@vidizmo.ai  ·  vidizmo.ai/integrations/catalog/onvif

Not what you need?

We build it

Send us your API documentation and we build, test and maintain the connector, at no development cost to you.

Request this integration

Bring an MCP server

If the system publishes a Model Context Protocol server, AI Intelligence Hub connects to it as a client with configuration alone.

Define a REST endpoint

Describe your endpoint and it becomes a node in an agent workflow, without waiting on our roadmap.

Product names, logos and trademarks shown here are the property of their respective owners. Their use does not imply any affiliation with or endorsement by them.