Google's free search model now handles audio and video, and runs on a phone
On 6th Oct'26, Google released EmbeddingGemma 2, an open model that turns text, code, images, audio and video into searchable vectors in one shared space. The weights are on Hugging Face and Kaggle under the Apache 2.0 licence, and Google says the text-only part runs in about 191MB of memory on a Pixel phone.
What it actually means
An embedding model is the part of a search system that decides which of your files match a question, and until now searching a library of product photos or call recordings usually meant sending them to a paid cloud API. This one is free to use commercially and small enough to run on your own server or a staff laptop, so a team sitting on years of client calls or creative assets can make them searchable without the files leaving the building. In a Gulf bank or a law firm, that is usually the condition for doing it at all.
The quality claims are Google's own, and its multilingual text scores barely moved from the first version, so test it on Arabic before you rely on it for a regional archive. Start with a few hundred of your own files and the questions people ask about them, then compare the results with whatever you use now.
Searching your own recordings no longer means uploading them to someone else's cloud.
Source: Google · Thursday 8 October 2026