TwelveLabs adds first person video analysis with Pegasus 1.6

The update adds image inputs and more detailed video segmentation.

Jordan Reid
October 6, 2026
AI Model Releases, Models, Tools
1 min

Hands at a photo editing workstation with an ocean image on a monitor and camera equipment on the desk — Illustrative editing workspace photographed by Jakub Zerdzicki on Pexels

Listen to this article

TwelveLabs released Pegasus 1.6 on October 6, adding analysis of video from wearable cameras and teleoperated systems.

The update also accepts up to 20 images in one request. TwelveLabs says it identifies people, objects and characters more consistently than Pegasus 1.5.

For developers labeling footage, the model can return events with timestamps inside individual video segments. Metadata extraction is also less tied to how those segments are defined.

Another change lets segmentation return the segments it produced even when the output is incomplete. Developers still need to account for partial results.

TwelveLabs directs users to update its Python or Node.js SDK to access the features.

Archival photograph by Jakub Zerdzicki via Pexels under the Pexels License. Existing optimized WebP rendition. It illustrates visual media work and does not show TwelveLabs, Pegasus or model output.

Jordan Reid

Jordan Reid is focused on AI tools, agents, developer products, and the way technology changes everyday work. Jordan approaches a launch from the user’s side of the screen. What can it actually help someone finish? The voice is practical, conversational, and skeptical of products that turn a simple job into five new settings. Coverage follows coding assistants, creative software, browser agents, and the workflows around them, with attention to pricing, permissions, setup, and the human work that remains.