Get the code and build your own video app. → https://goo.gle/3Kof8ad
In this video, Martin Omander and Ayo Adedeji show you how to build an app that "watches" and understands YouTube videos using Gemini 2.5 Pro. Forget complex data pipelines – with Gemini, you can achieve powerful, multimodal capabilities with just one API call! Replace brittle pipeline code with smart prompts to customize your app’s output for blog posts, summaries, quizzes, and more.
We’ll also cover how to integrate Gemini to generate both text content and header images from video input, discuss cost considerations, and explain how to handle longer videos with batch requests.
Get ready to see how the developer’s job in AI has fundamentally changed – it’s all about the skill of prompting an "all in one" model that can already see, listen, and reason!
Chapters:
00:00 – Intro
00:51 – Demo
01:30 – Code review
03:18 – Q&A
05:35 – Recap
Watch more Serverless Expeditions → https://goo.gle/ServerlessExpeditions
🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
#GoogleCloud #CloudRun #Serverless
Speakers: Martin Omander, Ayo Adedeji
Products Mentioned: Gemini 2.5 Pro
