Hello, @Jae Here I am the CEO of @TwelveLabs.
Today, we’re launching Pegasus 1.5, the first video language model for converting video into queryable data assets. If your video was as searchable as text, what would you create? Try the free playground: twelvelabs.io
Video is the most confusing source of data. It’s hard to know the content of your video without just watching the video. Pegasus 1.5 lets you understand your video library autonomously, on the fly, and at scale. In addition, it future-proofs your archive and enables agents to navigate it with enriched and custom-defined metadata.
What’s New:
Time-based metadata: Create custom, time-coded metadata based on your exact need. Some examples include: segments every time the speaker changes, every time my favorite basketball player dunks, and every time my logo appears on screen.
On the fly processing: Start with just one video, and get value immediately. If you’re a creator who needs to transcribe your content for YouTube and upload video to TwelveLabs, along with highlights, Pegasus 1.5 will give you exactly what you need.
Multimodal prompting: Pass an image, and ask the model to show you whenever something appears in the image. Try it for product placement or to track your favorite player in a game.
We are proud. Build a model that actually helps you understand your video content, the way you want it to. We outperform the top general models on segmentation and multimodal inputs. We support 2 hours of video, which is twice as long as other models. And, we are more cost effective. Check it out, and your feedback would be appreciated!