product · May 20, 2026
Elastic Introduces Jina v5 Omni Family Two Models to Power Text Image Video and Audio Search
Share the canonical public link.
Elastic announced jina-embeddings-v5-omni on May 11, 2026, a new family of multimodal embedding models with the ability to represent text, images, video, and audio as vectors. Available in small and nano sizes, the models share the exact same text embedding space as jina-embeddings-v5-text so existing users can swap in an omni model without rebuilding indexes. Developers can now perform search, classification, clustering, and deduplication across different media types in a single semantic space. Elastic (NYSE: ESTC) the Search AI Company made the announcement from San Francisco on May 11, 2026.
Below validation threshold — auto-passed without scoring