AI that truly understands video. Uses multimodal models (Marengo/Pegasus) to search, analyze & generate text from video content at scale.
This is the 8th launch from TwelveLabs. View more
Jockey by TwelveLabs
Launching today
Jockey is the first AI that understands your entire media library across photos and video. It analyzes thousands of hours of footage so you can find and connect people, moments and context across videos. Use it in Claude or ChatGPT, or build with the API/SDK. Ingest YouTube, TikTok and Instagram Reels links; assemble content into MP4s; and create and share video-driven artifacts with playable clips. Every TwelveLabs model upgrade makes Jockey better, without re-integration.
Launch Team
Great that Jockey understands my whole photo and video library, so I can describe a clip in plain words and actually find the right footage.
@karimbenkeroum exactly! try for free here: playground.twelvelabs.io/get-started
Keeping timestamped clips and JSON in the output gives developers something they can actually build on. The ability to revoke shared results is a thoughtful detail too, especially when the footage isn't meant to stay public.
exactly - that's video understanding, as an API. Developers would love it. See docs: docs.twelvelabs.io
Congrats Aiden and the TwelveLabs team on taking Jockey to GA. Pairing your own library with a social corpus of trending Reels and TikToks is the part I want to try, since most video search tools only see what you uploaded. When Jockey explains why a hook works, is that grounded in performance data from the corpus or in Pegasus reasoning about the clip itself, and can a user tell which one an answer came from?