Learning Timeline
Key Insights
Specific Model Requirement
The 'Stream real-time' feature only works with the 'Gemini 2.0 Flash Experimental' model. Older model versions do not support this low-latency visual interaction.
Low Latency Benefits
Gemini 2.0 is designed for 'Low Latency', meaning the AI can see your screen, hear your voice, and respond almost instantly—similar to Advanced Voice Mode—without having to wait for long video upload processes.
Free Access
You can currently try this feature for free in Google AI Studio without needing to add credits or subscribe to a paid plan.
Prompts
Visual Analysis & Data Comparison
Target:
Gemini 2.0 Flash Experimental
Tell me what the difference between Gemini 1.5 Pro 002 and Gemini 2.0 flash experimental are on the various benchmarks that you can see here.
Computer Vision Test
Target:
Gemini 2.0 Flash Experimental
What do you see? What is this gesture? What am I doing?
Step by Step
How to Enable the Real-time Streaming Feature in Google AI Studio
- Open the Google AI Studio website.
- In the right-hand panel, click the 'Model' dropdown menu and select 'Gemini 2.0 Flash Experimental'.
- Click the 'Stream real-time' button located at the top of the workspace.
- Click 'Allow' on the browser pop-up to grant access to your camera and microphone.
- To share your screen, click the 'Share screen' icon (usually a screen icon or found within the streaming menu).
- Select the 'Window' or 'Chrome Tab' you want to show the AI, then click 'Share'.
- Start interacting by speaking directly or typing a prompt to ask about what is happening on your screen or camera.
