Google expands EmbeddingGemma beyond text to images, audio and video

# Google's New AI Can Now Understand Pictures, Sound, and Video Together Google released a new AI tool called EmbeddingGemma 2 that's small enough to run on your phone and can now understand text, images, audio, and video all at once—something the previous version couldn't do. This means apps could potentially search through all types of content or compare a photo to a song in ways that weren't possible before. Since it works on smartphones rather than requiring powerful computers, it could enable new features in everyday apps without needing to send your data to the cloud.
Google LLC today released EmbeddingGemma 2, an open multimodal embedding model small enough to run on a smartphone. The release takes the EmbeddingGemma line beyond text, which was all the first version handled when Google introduced it in September 2025. Images, audio and video now share one embedd
More from Best AI Tools
Get new guides every week
Real AI income strategies, tool reviews, and plain-English news — free in your inbox.
