chatsaxSearch foundation
Back to News
Press release7 min read

jina-embeddings-v5-omni: Embeddings for Text, Image, Audio and Video

Han Xiao · Jina AI
jina-embeddings-v5-omni: Embeddings for Text, Image, Audio and Video
Image source: Jina AI / original publisher · Original publication

Reading summary

Introduces the v5-omni family and its shared representations across four input modalities.

A Chatsax reading summary of an original Jina AI publication.

Models in this article

jina-embeddings-v5-omni-nanojina-embeddings-v5-omni-smalljina-embeddings-v5-text-nanojina-embeddings-v5-text-small

Read the original research

Read the full publication for methods, examples, evaluation conditions, and limitations.

Read on Jina AI