Beyond Video Transcription: How to work with Videos in Gemini 2.5 Pro Experimental in Swift

Learn how to work with Google Gemini 2.5 Pro Experimental in Swift to process video, generate detailed summaries, and extract key information using images, search tools and more!

Google just released Gemini 2.5 Pro Experimental, and it’s a true game-changer for video processing. Compared to the earlier Gemini 2.0 Flash model I experimented with a few months ago, this new model can handle up to an hour of video in one go—no more tedious chunking (unless you’re dealing with ultra-long videos). The expanded context window is simply impressive!

So, what can it do and how can you work with this model in Swift? Let’s dive in 🤿