Google Gemini Full Tutorial 2025: Every Feature Explained (Including Google AI Studio)

Key Takeaways

Hey everyone. In my last video, I introduced you to Chat GPT. Today, we're going to talk about Google Gemini. I'll walk you through everything from the basics to some advanced features. Google Gemini started out as Bard, which launched in early 2023, around 4 months after Chat GPT. Then in February 2024, Google officially renamed Bard to Gemini. Currently, Gemini is the second most popular large language model out there. I've been using Google Gemini myself for a while now, and here are a few things that really blew me away. Number one, Gemini integrates really smoothly with Google services like Workspace, documents, Gmail, Google Drive, Google Maps, and YouTube. Number two, Gemini is built as a multimodal model, meaning it can handle well text, audio, images, and even videos. Its video recognition ability is especially impressive. I'll show you more on that later. And number three, Gemini's latest model and its advanced deep research feature are currently free to use. They also offer a one-mon free trial for their paid version, Gemini Advanced. Overall, Gemini is a super powerful generative AI chatbot, and I'm excited to dive in deeper. All right, let's get started. Here's what you'll see once you've logged into Gemini. Right in the center is your main chat window. Down here at the bottom, you can type directly to chat with Gemini. Up on the top left, there's a menu button. When you click on it, you'll see your previous conversations. Scroll down a bit and you'll find something called gems. These let you customize your own Gemini Assistant. Below that, you've got various settings options. Over on the top right, there's another menu. Just like other Google services, this gathers all your Google tools in one place, so it's super easy to switch between them. Now, in the upper middle area, slightly to the left, you'll see where you can choose your model. Since I'm using the paid version of Gemini, it shows Gemini Advanced here. But just so you know, both free and paid users currently have access to the same five models to choose from. First, there's 2.0 Flash. This one's great for quick replies to everyday questions. It's fast and efficient. Then we've got 2.0 Flash thinking, which is a bit more advanced than Flash. It handles slightly more complex questions with better reasoning. Going a step further, there's 2.5 Pro. This just came out last month. It's designed for more complex tasks like academic writing, technical analysis, or business strategy. It also has much stronger reasoning abilities. It's actually the most powerful model Gemini has right now. Next is deep research with 2.5 Pro. This one's perfect for professional level research like market studies or in-depth analysis. It gathers a bunch of information and gives you a full report. And finally, there's personalization. This model uses your Google search history to give you more personalized responses. All right. Now, let's go ahead and take a closer look at Gemini's features one by one. First off, you can just type your question directly into the chat box at the bottom. Let's try asking something like, "How does raising tariffs affect international trade relationships?" If you're using the 2.0 flash model, the response comes back super fast. Scroll all the way down and you'll see a few options. You can give a thumbs up, ask it to redo, or even share the response. Inside more icon, there's a feature called doublech checkck response. This highlights the sources Gemini used so you can verify the info it's giving you. There's also a texttospech option that lets you hear Gemini's answer read out loud. All right. You'll notice that the question we just asked now appears in the chat history on the left. If you click new chat, it'll open up a fresh chat window. Now, a quick explanation on prompts. Basically, whatever you type here to ask Gemini, that's your prompt. And the better your prompt, the better Gemini's response will be. Of course, crafting a good prompt is a whole topic in itself. So, we won't go too deep into that here, but here are a couple of simple tips. Try to be as clear and specific as possible. And if you can provide a bit of context, it helps Gemini understand your question better. If you're totally lost on how to write a good prompt, the easiest thing to do is just ask Gemini how to write one. Then use its suggestion as your actual prompt, and you'll probably get a pretty solid result. Next, let's take a look at the add files button. You can use it to upload images, documents, or even link directly to your Google Drive. For example, let's say I upload Palanteer's 2024 financial report. It's a PDF with over a 100 pages. I can ask Gemini to summarize the key points or even ask specific questions about the content in the file and it'll find the answers for me. This really cuts down the time we'd normally spend digging through documents. So, first I ask it to look up info related to revenue, net income, operating income, and EPS. Gemini quickly pull out the relevant data and even tell me which page in the PDF the info came from. Then I ask the major revenue streams for Palunteer. Again, it is able to grab that info super fast. All right, now let's check out the image upload feature. This feature is especially handy on your phone. For example, when you're out and about, you can snap a photo of something interesting and ask Gemini for insights or suggestions on the spot. Let's say I upload a photo of a menu I saw during a trip to Japan, and I ask Gemini for some recommendations on what to order. At the same time, I switch my model to the most advanced one, 2.5 Pro. With 2.5 Pro, the response time is a little slower, but you'll get much more detailed results. It gave me a full breakdown and at the end, some helpful suggestions on what to order. Even if I don't understand Japanese, I can still order confidently just by using this feature. Next up, let's try out the deep research feature. Here, I ask Gemini to analyze the current landscape of AI tools, what they're used for, and who the main users are for each one. Before diving into the research, Gemini first shows you its stepbystep plan for how it'll tackle the question, so you get a sense of its thought process. If the plan looks good to you, you can just hit start research. Now, it's started the analysis. While it's running the analysis, you can check in on its progress and see which websites or sources it's been searching through. After waiting a little while, Gemini finally finished the deep research. And right here, you can see the full report it generated. The content is super detailed. With Gemini's deep research feature, you can quickly gather a large amount of info, organize it neatly, and get a complete breakdown of your topic, all without spending hours doing it yourself. Plus, it includes proper citations for everything, so you can be confident that the info is accurate and trustworthy. Once the research is done, there's this export to Docs button. You can click it to save the whole report straight to your Google Docs. On the left side, there's also a quick outline preview so you can jump around the report easily. All right, jumping back into the Gemini interface, there's another really cool feature called generate audio overview. This one takes the results from your research and turns it into a spoken conversation. It's usually two voices having a dialogue, kind of like a podcast, where they walk through the content together. And honestly, it's an engaging way to absorb info. And just like that, it generated an audio file. Okay, so we're diving into AI tools in 2025 today. And you know, it's kind of crazy how much everyone's talking about them. Yeah, it really feels like it's everywhere right now. It is super cool. There are two people having a conversation and the voices sound really natural, almost like real humans chatting. All right, so that's the deep research feature in Gemini. Now, let's move on and take a look at the next feature, Canvas. The Canvas feature lets you co-edit directly with Gemini. And if you're using it for coding, you can even preview the code output instantly. So, here I ask Gemini to help me build a website that organizes a bunch of popular AI tools with one-click links to each of their official sites. I also tell it to categorize the tools by type. Okay. Now, over here on the right, the canvas area starts generating the code. Once Gemini finishes writing the code, you can just click the preview button on the right to see how it looks. And yeah, it actually looks pretty solid. Plus, the links really do take you straight to each AI tools official website. If there's a part of the code you don't understand, you can just ask Gemini right there. It'll explain the code for you on the spot, which is super helpful for learning. And if you want to tweak something, just type your request into the chat box. Gemini will update the code for you. For example, I wanted to add a search bar so users can quickly find a specific tool. So, I tell Gemini that, and it modified the code right away. So, once Gemini finishes making the changes, there's a search bar that lets you quickly find tools. Also, if you click this icon, it'll highlight the parts that were changed so you can easily compare before and after. Now, let me show you another example of using Canvas. This time, I asked Gemini to come up with five creative ways to use Google Gemini. Same deal. You can highlight specific parts of the content, then ask Gemini to revise it or give you more info. Down here in the lower right corner, there are a few options. First, you can adjust the length of the text. Make it longer or shorter. For example, I chose long, and Gemini added more details to the section. You can also change the tone of the writing. Make it more casual, more formal, whatever fits your style. Another useful option is editing suggestions. You'll see comments pop up on the side of the article with recommendations on how to improve it. If you like the suggestions, you can just accept all of them and they'll be added to your draft automatically. So, using Canvas, you can co-edit with Gemini in a really interactive way, refining and building up your content together. Now, let's move on to the next feature, create image. Right now, there isn't a specific button in the Gemini interface labeled create image. If you want it to generate an image, you just need to type create image directly into your prompt. Gemini will understand and start creating. For example, I described a scene with some visual details and asked it to generate an image based on that. And here's what it came up with. An image that matches my description. Now, let's talk about how Gemini connects with other Google services like Gmail, Google Drive, YouTube, and more. Just type an add a symbol in the chat box and it'll show you a list of services it can connect to. For example, it can sync with tools in Google Workspace like Gmail, Drive, and Docs. So, you can quickly search or summarize content from those places. Here, I asked it to find emails in Gmail that include attachments. It pulled them up for me, and I could even click to open the emails directly. You can also link to Google Flights or Google Maps to plan a trip. And the YouTube integration is super useful. It can pull out key points from a video. Here's an example where it listed out the main takeaways from a video I asked about. You can even click to watch the video right from the result. If you want to explore this feature further, go to the settings in the bottom left corner, then click on apps. It gives you a detailed breakdown and some example use cases too. All right, now let's dive into the gems. Gems are like GPTs in chat GPT, a way to create more personalized assistance. Google already has some pre-made gems available that offer specific functions. But aside from using those, you can also create your own gems. So, when would you want to make one? If you find yourself repeating similar questions or working with specific types of info, making your own gem is a great timesaver. Here's an example. I go into gem manager, click add new gem, and write a prompt about researching top rated home appliances. Once that's set up, I just need to type in the type of appliance like TV, and it'll follow my instructions, pulling up suggestions and even including links. I don't have to repeat the full instruction every time. If you're not sure how to write the instruction, there's a button to let Gemini rewrite it for you. Also, under the knowledge section, you can upload files. Your custom gem can then use the info in those files when responding. Let's try out the home appliance assistant I just made. Say I want to buy a TV. It gives me a full response based on my earlier instruction and includes product links, too. If I want to switch to another item, I just type in the new product name. Having a custom gem like this really makes repetitive tasks much more efficient. Okay, so that pretty much covers all the main features you can use in the Gemini web interface. Earlier I mentioned that the models available in the free and paid versions of Gemini are actually the same. So what extra do you get with the paid Gemini advanced plan? First, you can use Gemini directly inside Google services like Gmail, Google Docs, Sheets, and Slides. This means it can help you summarize emails, generate writing suggestions, recommend table formats, and more right inside those tools. Second, you get access to Notebook LM Plus. Notebook LM is another Google product that automatically summarizes reading materials and creates study notes. It's a really powerful tool and I'll probably make a dedicated video on that in the future. Third, you can use VideoGen in Google AI Studio. This is a brand new video generation tool recently released. Let me go ahead and show you how Gemini integrates with Google Docs to streamline your work. All right, let's head over to Google Docs and create a new document. You'll see the Gemini icon up in the top right corner. Just click it to open the panel. You can type your own prompt here or choose from the sample suggestions at the top. For example, I ask it to help me write a blog post. It even gives me a pre-written prompt which I just go ahead and use. Click insert and it pastes the content into your document on the left. From there, you can make edits yourself or continue refining the content with Gemini's tools. Now, let's check it out in Google Slides. Just create a new presentation. Gemini will be in the top right corner again. I select one of its sample prompts to see what it could do. It actually created a slide deck with images included, which is super helpful because it saves you the trouble of hunting for visuals. Definitely a timesaver. So yeah, this shows just how powerful the Gemini integration is across Google services. All right, heading back to the Gemini web interface. Now, aside from using Gemini on its main site, there's another place you can try it out, Google AI Studio. This one's more geared toward developers, so the interface is a bit more complex, but regular users can absolutely explore it, too. And a big plus, new features usually roll out to AI Studio first. Quick overview. On the left, there's a chat section that works just like the regular Gemini interface. You can talk to it directly. On the right, you can choose your model. One interesting option here is 2.0 flash image generation. With this model, you don't have to type create image. You just describe what you want and it starts generating images right away. There's even a row of sample prompts below to help you get started. As for the other models, most of them are already available on the main Gemini site, too. Below that, there are more advanced controls where you can fine-tune Gemini's behavior and output. I won't go into too much detail here, but if you're interested in learning more about Google AI Studio, let me know in the comments. I'd be happy to make a separate video on it. Aside from regular chat, there's one more powerful feature I want to introduce. Stream. With the stream feature, you can have realtime conversations with Gemini. And even cooler, you can let it access your webcam or share your screen so it can interact with what you're seeing in the moment. Here's a simple example. How many models do you see here when using Gemini Advanced? In the Gemini Advanced options, I can see the following models. Two, zero flash 2.0 No flash thinking experimental 2.5 Pro experimental deep research with 2.5 pro and personalization experimental. Would you like me to elaborate on any of these? Just like that, Gemini can read what's on your screen and respond based on what it sees. Super interactive. Next up is a really cool feature called Video Gen. This one lets you generate short videos from either images or text prompts. It just launched a few days ago and right now it's only available for paid Gemini advanced users. Down here you'll find some example. You can either upload an image and ask it to create a video that expands on that scene or just type a full text prompt and it'll generate a video from scratch. I tried one of the built-in examples to generate a new video. Here's the result. Not bad at all. It's still an early feature, but I'm sure the quality will only get better with time. By the way, a quick tip. On the right hand side of the chat interface, there's something called the prompt gallery. It's full of example prompts to help spark ideas and show you different ways to use Gemini. All right, that pretty much wraps up how Gemini works inside Google AI Studio. That's it for today's walkthrough of Google Gemini. We've covered all the major features and gave you a general look at how each one works. If there's any part you'd like me to go deeper into, feel free to drop a comment down below and let me know. I'm happy to make a follow-up video with more detailed explanations. In the next video, I'm planning to cover either Deep Seek or Claude, so stay tuned. Make sure to like, subscribe, and turn on the notification bell so you don't miss it. All right, that's all for today. See you next time. Bye.