How to Use Gemini's Live Voice and Camera in Your Daily Life

Imagine standing in front of a tangled mess of cords behind your entertainment unit, wondering which plug goes where. Instead of typing a clumsy description into a search engine, you can now simply point your phone's camera at the cords and talk to an AI assistant about what you see in real time.

Talking and showing: A new way to interact

This hands-free interaction is made possible by Gemini's multimodal capabilities. The word multimodal simply means the AI's ability to process and understand different types of information—such as text, voice, and live video—all at the same time, rather than just reading typed words.

When you use these features, the AI can "see" through your camera lens and "hear" your voice with almost zero latency (the annoying delay or lag you sometimes experience with older voice assistants). This means you can have a natural, back-and-forth conversation just like you would with a friend standing next to you. You do not need to wait for the assistant to finish speaking before you reply; you can interrupt, ask for clarification, or change the subject mid-sentence.

Three practical ways to use Gemini's eyes and ears

• Interactive troubleshooting: If your bicycle chain keeps slipping or a strange warning light appears on your washing machine, you can open your assistant, point the camera at the issue, and ask for help. The assistant will guide you step-by-step through the fix.
• On-the-spot learning: If you are out walking and spot an unusual bird, plant, or building, you can show it to the AI. It can instantly explain what you are looking at, tell you about its history, or even translate signs written in other languages on the fly.
• Creative kitchen help: Stuck with a fridge full of random ingredients? Lay them out on the kitchen bench, show them to your assistant, and ask for recipe ideas. You can talk through the steps and adjust the recipe as you cook without getting sauce on your screen.

How to start a live session

To start using these features, you only need your smartphone and the official Gemini app.

1. Open the app on your phone.
2. Look for the waveform icon (a small button that looks like moving soundwaves) in the bottom-right corner of your screen.
3. Tap the icon to start a live voice conversation.
4. To let the assistant see your surroundings, tap the camera icon within the chat screen to turn on your live video feed.

You can now speak normally, ask questions, and point your camera at whatever you want to discuss.

Wrap-up

Using AI is no longer about sitting at a desk and typing perfect prompts (the written instructions you give to an AI to