AI & Creative Tools
One 740M Model That Puts Your Images, Audio, Video and Text in the Same Vector Space
Searching a mixed-media archive normally means a separate embedding model per modality and no way to compare across them. This one embeds text, code, images, video and audio into a single shared space — 270M text backbone plus modular 170M vision and 300M audio encoders, with Matryoshka truncation for 6x smaller vectors.