Fast Video Cataloger 10.4 adds plain-language visual search

VideoStorm has released Fast Video Cataloger 10.4 for Windows with a new visual search tool that finds shots from plain-language descriptions without prior tags or cloud upload. The update also expands Trained Tags and keeps search, indexing and footage local on the user's machine or server.

Why it matters: - Editors can now find shots by describing what they look like instead of relying on memory, tags or manual scrubbing. - The local-first design matters for teams that want footage and indexes to stay on their own machines. - The update could speed up search across large libraries where footage was never logged or was logged with different wording.

What happened: - VideoStorm released Fast Video Cataloger 10.4, the latest version of its Windows video cataloging software. - The main new feature is visual search. - An editor can type a plain-language description such as “drone shot over a city at night” and get matching scenes from the library. - The software searches the images themselves, not keywords. - Fast Video Cataloger 10.4 is available now for Windows 10 and 11. - Pricing starts at $9.90 per month, $97 per year, or $197 for a perpetual license. - A free 30-day trial is available at the product website.

The details: - Visual search works with the other filters in the Search window. - Searches can be limited to a folder or a project keyword. - The feature can surface footage that was never tagged. - Find similar scenes sorts the catalog by visual similarity after an editor finds one good shot. - The tool can pull up the rest of a sequence or every take from the same location. - The best matches appear first. - Each video gets a limited number of results by default, so one long shot does not fill the list. - The search index is built on the user's own computer while videos are indexed. - Older catalogs can be updated in a separate pass. - That pass shows how much of the library is covered and can be paused and resumed. - The footage and the index never leave the user's machines. - In a shared catalog, the search runs on the Fast Video Cataloger server. - The server also exposes the search to scripts through the REST API and to AI assistants through MCP. - Fast Video Cataloger works alongside editing tools such as Premiere Pro and DaVinci Resolve. - The software is built for search and organization, with visual browsing and structured metadata stored locally. - Version 10.4 also includes smaller fixes and improvements. - The full list appears in the version history in the user guide. - Version 10.4 improves Trained Tags, a feature introduced in version 10.3. - A trained tag is a custom AI keyword taught from a handful of example thumbnails. - A wrong match can be right-clicked and marked “Not this.” - The keyword is removed after that correction. - The Trained Tags window also flags examples that make a tag worse, including near-duplicates. - Fredrik Lönn, co-founder of VideoStorm, said visual search lets editors look for shots the way they remember them.

Between the lines: - VideoStorm is positioning Fast Video Cataloger as a search layer, not an editing replacement. - That approach targets the pain point of finding footage fast, especially in libraries with inconsistent or missing metadata. - The local processing and shared-server options suggest the product is aimed at both solo editors and larger teams with stricter data-control needs.

What's next: - Editors can start using visual search now on Windows 10 and 11. - Teams using shared catalogs can connect the feature to scripts through the REST API and to AI assistants through MCP. - VideoStorm says the release includes additional fixes and improvements beyond the headline features. - More version details are available in the user guide's version history.

The bottom line: - Fast Video Cataloger 10.4 turns a video library into a searchable visual archive, with plain-language search, local indexing and better correction tools for AI tagging.