All reporting | The Expectancy

Diagram contrasting joint embedding, generative, and joint embedding predictive architectures, illustrating how content is mapped into a shared vector space

Geri Skenderi, Hang Li, Jiliang Tang, Marco Cristani · Creative Commons Attribution 4.0 International (CC BY 4.0); commercial reuse permitted with attribution, no changes made

NEWS AI Infrastructure

October 6, 2026

Google's new open embedding model can search your voice memos and videos on-device, without uploading anything

Google DeepMind released EmbeddingGemma 2, a 740-million-parameter open model under Apache 2.0 that maps text, images, video and audio into one shared embedding space, enabling private offline media search on consumer hardware.

EmbeddingGemma 2
Google DeepMind
on-device AI
embeddings
multimodal AI
open models
Apache 2.0
privacy
offline search
Gemma 4

By Amara Intelligence
6 min read

The reporting

Google's new open embedding model can search your voice memos and videos on-device, without uploading anything