09 October, 2026

What's New in Jumper - October 2026

Named reference photos for people, automatic speaker naming, Summary Analysis exports, more ways to filter your footage, and the official launch of Jumper Enterprise.

Jumper v2026.10.09 is now available for macOS on Apple silicon and Windows. On macOS, update through Auto-check for updates in the Jumper launcher. On Windows, download and run the latest installer.

Put names to faces and voices

You can now supply named reference photos before People analysis. Jumper uses them to automatically name matching face groups as it analyzes your footage. If you already know your cast or interview subjects, this saves you a round of naming groups by hand.

The same feature works when an AI agent starts analysis through MCP, so reference photos can also be part of an agent’s setup for a research or editing task.

Once you have named people in a Face Collection, Jumper can use them to automatically name transcript speakers, too. You can do this after analysis or from the People tab, making it easier to connect who’s on screen with who’s speaking.

Take your summaries with you

Summary Analyses can now be exported as PDF, Word, or plain text. Choose an overview, all levels, or detailed sections depending on how much of the analysis you want to include.

Share a concise overview with a producer, bring detailed sections into a paper edit, or keep a text copy alongside your research notes. The summaries you use to navigate footage in Jumper are now easier to share outside the app.

More ways to narrow down your footage

The Media view now lets you filter files by people, Tag Collections, marker colors, and named speakers, alongside the existing filename, folder, metadata, and analysis filters. That makes it easier to focus on the files relevant to the job before you start searching.

Speech search also gains filters for Tag Collections and marker colors, which you can combine with speaker and metadata filters. For example, you can look for a quote from a particular speaker within a collection of interview selects.

And in visual search, you can now search for selected people without entering a text query. When the person is all you need to find, just select them and search.

Jumper Enterprise is now available

We’ve also officially launched Jumper Enterprise for studios and teams. It includes everything in Jumper Pro, plus central license management, company SSO, configuration you can distribute to seats, policies for controlling access to features and analysis folders, and dedicated support.

Read more on the Enterprise page and in the Enterprise documentation.

Improvements and fixes

R3D and NEV audio: Speech Analysis now supports audio embedded in R3D and NEV footage. Thanks to Mr. Berns for reporting this.
Windows transcription: English transcription with Parakeet now works on the CPU, including computers without an NVIDIA GPU. Thanks to Ro for reporting this.
Tag Collection timing: Fixed speech segments losing their exact timing when bulk tagging or editing tagged clips.
Final Cut Pro navigation: Fixed clip navigation failures while the browser was refreshing. Thanks to danwinckler for reporting this.

As always, we’d love to hear your feedback. Join us on Discord to share ideas and let us know how the update fits into your workflow.