Home > AI > AI How To

How to use Google Gemini AI model – our step-by-step guide

The new capabilities of Google's AI chatbot

Reviewed By: Steve Hook

Last Updated on February 10, 2024
How to use Google Gemini. Using and building artificial intelligence applications with Google's AI model.
You can trust PC Guide: Our team of experts use a combination of independent consumer research, in-depth testing where appropriate - which will be flagged as such, and market analysis when recommending products, software and services. Find out how we test here.

Google welcomes us to the “Gemini era” with the release of the Gemini AI model. On December 13th, 2023, Bard got its biggest upgrade yet with Gemini Pro. Its most powerful version, Gemini Ultra, outperforms OpenAI’s GPT-4 “in most tests” according to Google CEO Sundar Pichai. Indeed, Google DeepMind CEO Demis Hassabis affirms that Gemini is “better than any other model out there”. This claim is substantiated by various generative AI academic benchmarks including MMLU (Massive Multitask Language Understanding).

How to use Google Gemini AI

Google Gemini is the AI (artificial intelligence) model powering the Google Bard chatbot. You could call Gemini the ‘brains’ of the operation.

In this way, it is similar OpenAI’s GPT-4, GPT-4V, or GPT-4 Turbo. Google Gemini isn’t an AI chatbot like OpenAI’s ChatGPT. Most news publications will conflate Gemini and ChatGPT. After all, ChatGPT makes headlines (at the cost of accuracy). In other words, read PC Guide.


Top 5 Cyber Monday deals

This year's Cyber Monday has officially kickstarted, offering up huge discounts on some of the market's leading tech products. Below, we'll list the best Cyber Monday deals we can find.

Prices and savings subject to change. Click through to get the current deal prices.


Welcome to the Google Gemini era.
Welcome to the Google Gemini era. Photography: Steve Hook, PC Guide

First teased at Google’s Developer I/O conference, Gemini was rumored to be powerful. The launch event itself did not go over smoothly. Despite the imperfect reception, the model itself showed impressive early results which won back the faith of enthusiasts.

OpenAI’s ChatGPT model GPT-4 has fierce competition, make no mistake. Multimodality is a key focus of AI chatbot technology, and Google’s own is no exception. With Gemini now powering Google Bard, its capabilities in the audio and visual verticals are set to (potentially) overtake ChatGPT. Here’s a step-by-step guide about how to access it.

How do I access Google AI Gemini? A step-by-step guide

Step

1

Access Google Bard

Google Gemini is accessible via the AI chatbot known as Google Bard. The first step in using Gemini is to head to the Bard website.

There is no mobile app for Google bard, but this will undoubtedly be released later on in 2024.

Step

2

Understand multimodality

Google Gemini is built for multimodality — which includes text, images, video, audio, and code. In other words, there are plenty of ways to use Gemini!

To use it effectively, you’ll want to have any multimedia you plan to use at hand. You’ll also need to be aware of the capabilities of the version you’re working with, which could be Google Gemini Ultra, Gemini Pro, or Gemini Nano.

Step

3

Access requirements

To access Google Bard, you’ll need to be signed in to a Google Workspace account which has Bard access enabled.

This AI chatbot also has a minimum age requirement of 18 years old.

Step

4

Using Google Bard features

With Bard open, you can add your image media, type a text prompt, or talk to Bard. It will transcribe your voice command and process it the same way as a text prompt.

When using image media, you can review your uploaded images in your pinned and recent chats in Bard. You can also delete your prompts, which deletes any images you upload in those prompts, in your Bard activity.

Google Bard AI chatbot homepage
Google Bard @ PC Guide. Photography: Steve Hook, PC Guide

What can Google Gemini AI do?

The most powerful version of Gemini is more than an LLM (large language model). In fact, it’s a VLM (visual language model) enabling the Google Bard chatbot to perceive images in a surprisingly human way, and even create its own images. With current state-of-the-art multimodality, it can do anything other chatbots can do.

As with any other AI chatbot, it can also write new text or summarize existing ones.

Can Gemini write code?

Yes, Gemini can write code in various programming languages. It can even take an input image, and generate code that will recreate the visual stimuli as a website or app.

Can Gemini generate AI images?

Yes, Gemini can create AI-generated images. It can even create images that have text written in them (text-in-image generation).

Essential AI Tools

More Deals Coming Soon!

Can Gemini translate languages?

Yes, but that’s not the most impressive thing about it. Google Translate has been capable of that for years, but Gemini can reason across languages, translating the meaning of a foreign text. It can even draw its own conclusions about how closely the translated language carries the meaning and intent of the original language. The Google Bard chatbot can also do this visually when provided with an image prompt.

Does Google Bard use Gemini AI?

Yes, Google Bard is powered by Gemini. Google Pixel 8 users will also have first-access privileges to new features.

Steve is an AI Content Writer for PC Guide, writing about all things artificial intelligence. He currently leads the AI reviews on the website.