Which browsers support screen sharing in Google AI Studio?

Chrome and Chromium-based browsers like Edge have the most consistent support for the Live API screen-sharing feature. Safari and Firefox may not support all features. Check Google's AI Studio documentation for the latest browser requirements.

Can the AI model see everything on my screen when I share it?

The model sees the window or tab you selected when granting permission. Sharing a specific tab limits exposure to that content. Sharing the entire screen lets the model see everything visible on your display, including other applications that come to the foreground.

Is there a recording of what the AI saw during a screen-sharing session?

No. AI Studio Live sessions do not produce an automatic recording. If you want to keep what was discussed or discovered, save notes before closing the session.

What if the screen-sharing icon does not appear in AI Studio?

The screen-sharing feature is in the Live API section, not the standard Prompt editor. If you do not see a Live section, your account may need to be eligible for the Live API, which may require a Google API key or a specific account type.

How to Share Your Screen in Google AI Studio

Google AI Studio's Live API lets you share your screen with a Gemini model in real time. Here is how to set it up, handle permission prompts, and fix common problems.

October 14, 2026Updated October 21, 20265 min read

Google AI Studio at aistudio.google.com (opens in a new tab) has a Live API section that lets you share your screen with a Gemini model in real time. The model watches your screen content and can respond to what it sees alongside what you say or type. This is different from uploading a screenshot — the model receives a continuous stream, so you can ask questions about what is currently visible. Tools like fenbs let you save the useful observations, fixes, and context notes from a Live API session so the next AI you open starts from what you already learned, rather than working from scratch.

Screen sharing in AI Studio runs in the browser and uses the standard browser permission system for display capture. It does not install anything on your computer, but it does require Chrome or a Chromium-based browser for full support.

Where to find the screen-sharing feature

Screen sharing is part of the Live API in AI Studio, not the standard Prompt editor. To access it:

Open AI Studio (opens in a new tab) and sign in with your Google account.
Look for a "Live" option or "Live API" section in the left sidebar or the top navigation. The UI changes as Google updates AI Studio, so the exact label may vary.
Once you are in the Live API interface, you should see options for microphone input, camera input, and screen sharing.
Click the screen-sharing icon (usually a monitor or display icon) to start sharing. Your browser will ask which window or tab to share.
Select the window or tab you want the model to see and click Share.

If you do not see a Live API section, check that your Google account has access to AI Studio. Some features are available only with a Google API key or specific account types.

Browser permission requirements

The first time you start screen sharing, your browser will show a permission dialog asking what to share: your entire screen, a specific application window, or a specific browser tab. Choose the option that is least likely to expose content you did not intend to share.

A specific tab is the safest choice when you want to show one piece of work without exposing other applications or files.
A specific window works for showing a desktop application.
Entire screen is available but shares everything visible on your display, including notifications and any other windows that move to the foreground.

If you dismiss the permission dialog without choosing or if you click "Don't allow," screen sharing will not start and you will need to click the icon again. If the browser remembers a previous denial, you may need to reset permissions in your browser settings for the AI Studio site.

Common problems and fixes

No screen-sharing icon: you may not be in the Live API section. Return to the main AI Studio navigation and look for a Live or Multimodal Live section.
Permission dialog does not appear: check that your browser is not blocking pop-ups or permission prompts for the AI Studio domain. In Chrome, check site settings under the lock icon in the address bar.
Black or blank screen share: the browser captured the window but the display feed is not transmitting. Try sharing a browser tab instead of an application window, or refresh the page and start again.
Microphone not working alongside screen share: the Live API uses both audio and screen feeds. Make sure microphone access is also permitted for AI Studio in your browser settings.
Unsupported browser: Safari and Firefox may not support all features of the Live API. Use Chrome or a Chromium-based browser like Edge for the most consistent experience.

What to do after the session

A Live API session with screen sharing is interactive but ephemeral — there is no automatic record of what the model observed or suggested. If the session produced a useful fix, a better approach to a problem, or an observation worth checking, save it before you close the browser.

Findings from a screen-sharing session are particularly useful when they involve a repeating problem, a setup you will need to recreate, or a fix that took time to identify. Those are worth recording so the next person — or AI — dealing with the same issue can start from what you discovered.

How fenbs helps

Save what the session showed you before you close it

After a useful AI Studio Live session, add the key observation or fix as a context note in the relevant fenbs project. Note what was visible on screen, what the model flagged, and what you tried. The next AI you connect reads those notes at the start of the session — you do not have to recreate the screen-sharing setup to explain the same problem again.

Create a free account

Free for one person · No credit card · Works with Claude, ChatGPT, Cursor and more

How to do this with fenbs

Create a free account and open or create the project the AI Studio session relates to.
Run the Live API screen-sharing session and note what the model flags or suggests.
After the session, identify what was genuinely useful: a fix, a pattern, an approach that worked.
Add that finding as a context note in fenbs, with enough detail that someone else (or a future AI session) can understand it without seeing the screen recording.
Connect your AI apps at Integrations. The next session reads your project notes — the Live session findings are available without repeating the screen share.

For sharing AI Studio conversations as links, see how to share a Google AI Studio chat. For saving and managing your Gemini conversations more broadly, see how to save Google AI chat history.