Hey, I can’t find the screen sharing option on Google anymore—did they remove it?
Also, is it even possible to build an app that works just as fast? Or would the latency always be worse? If it’s doable, any idea how it’s typically built? Like, are there specific frameworks or libraries I should look into? What’s the actual logic behind it—does it stream video, take screenshots, or what?
I’m guessing it uses some combo of text-to-speech, video or image processing? Would appreciate any pointers to the right direction, thanks!
Hi @Bassam_El-Ashkar ,
Welcome to the forum !!
Google AI Studio Live offers a screen sharing mode that allows you to interact with Gemini AI in real time, turning it into a powerful learning partner or assistant that can “see” your screen and help with tasks, troubleshooting and learning new software. Here’s how to use this feature:
Step-by-Step Instructions
- Open Google AI Studio Live
- Select the Streaming/Live Mode
- Once logged in, look for the “Stream” button. This is where you can access the live features, including screen sharing and voice interaction
- Choose Your Model and Settings
- Select a model such as
Gemini 2.0 Flash 001. You may also choose your preferred voice and other settings.
- Start Screen Sharing
- Click the “Share Screen” button.
- You’ll be prompted to select what you want to share: Like Entire screen, Window, Chrome Tab
- Select your desired option and confirm by clicking “Share.”
- Interact with Gemini AI
- Once screen sharing is active, you can speak or type to Gemini. The AI will see what’s on your screen and can provide step-by-step help, answer questions, or guide you through tasks in real time.
- End Screen Sharing
- When finished, click the “Stop Sharing” or “Stop Share” button in the interface to end the session
Please let me know if you have any questions!
Thank you!