Gemini

How to create presentations in Gemini from a document using a single prompt

by

Let’s tell you how to create presentations with a single prompt wearing Gemini. This is a function with which you only have to add a document, and then ask the artificial intelligence to make the presentation based on the content of the file you are using. This feature is available to all users, both for free and paid. Of course, the result will always depend on the content of the document, its structure and its quality. The more complete and longer the document, the better the result will be. Create presentations with Gemini The first thing you should do is upload the file you want to use as a reference to create the presentation. You can do this by uploading the file from your computer or mobile, or linking it directly from Google Drive. Now, having the simple document, you have to add a prompt asking you to generate the presentation. You will then send this command along with the attached file. The one you can use is the following: “I am giving you this document. I want you to make a presentation to me with it.” Gemini will now take a few minutes to extract the information from the document, and will generate a presentation with several slides. The images will depend on the ones you have in the document, as well as all the content. Once you have the presentation created, you will have options to export or download it. If you export the document, it will go to your Drive as a Slides document, which is Google’s PowerPoint. And if you download it you will do so in a compatible format. In Xataka Basics | The best prompts to save hours of work and do your tasks with ChatGPT, Gemini, Copilot or other artificial intelligence

what it is, characteristics of this artificial intelligence model and differences with Gemini and ChatGPT

by

Let’s explain to you what is Kimi K2 Thinkingthe latest model of the company artificial intelligence Kimi AI. It is an AI that has made a name for itself today due to its open nature and for having managed to compete directly against GPT-5, Gemini 2.5 Pro and other high-end models. We are going to start the article by explaining what Kimi K2 is and the characteristics that make this artificial intelligence model different. Then, we will finish by telling you the main differences with respect to the most popular models on the market. What is Kimi K2 Thinking Kimi K2 Thinking is the latest version of Kimi, a Chinese artificial intelligence model created by Moonshot companyfrom Alibaba. Since the names are the same, you can clarify yourself by thinking that Kimi is the company’s AI, like ChatGPTand that this AI has different models that are being launched, such as the case of GPT-5 in the case of OpenAI. Kimi K2 was launched in July, and stood out for having a gigantic size of 10,000 million parameters. Now there is a new version called Kimi K2 Thinkingwhose number of active parameters amounts to 32,000. According to its creators, this allows the AI ​​to maintain stable use of agentic tools over 200 to 300 sequential calls. And what does all this talk mean? As you know, we are entering the era of AI agentswhich are automations with which an artificial intelligence can carry out different actions autonomously. This allows the AI ​​to even make decisions for you, from asking it to make your purchase to preparing a vacation package for you and taking care of the reservations. It is also something that at the business level is going to have even more uses. Therefore, the more ability an AI has to perform a large number of actions without making mistakes, the more valuable and powerful it is. Features of Kimi K2 Thinking The most important feature of Kimi K2 Thinking is that it is an open model. The models of companies like OpenAI, Google or Anthropic are closed, which means that their source code is kept under lock and key, only these companies know how it works inside. Meanwhile, K2 Thinking is open source, which means that anyone can know how it works inside looking your Githubits features, and you can even adapt it for free. What’s more, you can install it locally at no cost, although the computer needed for this is too powerful for ordinary mortals, but “distilled” versions, lowered or trimmed, can be released so that people can use them locally. In this aspect it is like DeepSeek, another open AI that already surprised a few months ago for approaching the power of non-open models such as Gemini or ChatGPT. In the case of Kimi K2 Thinking, according to the test benches has managed to surpass GPT-5something that until recently was unthinkable. We are facing a Mixture-of-Experts architecture model (MoE), which means that it is made up of several experts (subnetworks or specialized modules), and that not everything is activated at once, but only the parts of the model necessary to answer what you ask or perform the task that you have asked. It should also be said that it is multilingual, and can be used in other languages ​​although it focuses on Chinese, and that it can process many types of file formats. Also searches in real time to offer you the most up-to-date information, and is multimodal, being able to interpret text, images, code or a combination of these. Kimi K2 Thinking can be used as a conversational char answering questions and maintaining long context while following complex threads. But it can also interpret images, or a combination of mixed inputs such as images with text and with code. In addition to this, it can generate programming code, analyze long documents thanks to its large context window and extract information to answer questions about the content or give you a summary. Additionally, you can create automations or agents. Differences with ChatGPT or Gemini As we have told you above, the main difference of Kimi is its open concept. While ChatGPT and Gemini are proprietary models, Kimi allows access to the community so they can see its code. Several benchmarks have shown that Kimi K2 Thinking outperforms GPT-5 and Claude Sonnet 4.5 (Thinking) in search and agentic browsing in the browser, in text-only operation, and in information collection. The only thing in which it still does not surpass these models is in the creation of code. In the use of agentic tools, benchmarks or test benches have shown that Kimi K2 Thinking is positioned as a leading AI model. Besides, Kimi is a cheaper model for several things. First, training the model cost $4.6 million, according to indicate on CNBC, a ridiculous figure considering that training proprietary models like GPT-5 It cost about 500 million dollars according to estimates. It’s also cheaper to use the Kimi K2 Thinking API. The API is like the entry key that allows other applications to connect to this AI to work with it. The price of K2 Thinking is $0.6 per million tokens in and $2.5 per million tokens out. GPT-5 Chat costs $1.25/10 respectively, and Claude Sonnet 4.5 costs $3/15 respectively. For the average user, the operation is the same.. You have the website kimi.comwhere after registering for free you can use the Kimi K1.5 and K2 models. However, If you want to use Kimi K2 Thinking you will have to pay with their subscriptions of 19 or 30 dollars. At least, this is if you want to use the full version on the official website, without having to install anything. In Xataka Basics | The best prompts to save hours of work and do your tasks with ChatGPT, Gemini, Copilot or other artificial intelligence

Let’s say goodbye to Google Assistant a decade later. Google has begun to delete its code to leave only one option: Gemini

by

It’s not official but as if it were: the end of Google Assistant or the classic Google Assistant, is scheduled. An analysis of the latest version of the Google app for Android carried out by Android Authority has revealed his almost definitive goodbye. The Mountain View company is eliminating the code that, for the moment, allows us to choose between Gemini and the old assistant. It is the chronicle of a death foretold that ends an era within the company. Where before we saw the Assistant icon and dialog window, we now have the Gemini one. Image by Iván Linares for Xataka Android failed promise. Launched in May 2016, the Google Assistant was going to be a revolution. On paper, it promised full voice control of your cell phone, car and home. In practice, like many users have experiencedits use ended up being “despairing” although the “Okay, Google” It became popular in smartphones and speakers. Your inability to understand the context or natural language and the rise of AI models, has finished burying it. The future belongs to Gemini. With the rise of generative AI, Google has bet everything on Gemini, but it has had a rather confusing rollout. For months, the American company maintained a curious mess with several duplicate names, apps and services… Bard, Assistant with Bard, Project Astra… In practice, two assistants live on the same mobile phone. In February 2024, its “transmutation” began: that was when Google launched the dedicated Gemini app (Bard was left behind) on Android, which when installed was offered as a replacement for Assistant. As we tested in its day, the new AI took over of the invocation with the famous “Hey Google” command. A more mature replacement. The problem with the Gemini assistant is that, at first, it was quite green. It was a powerful chatbot, but a not so useful assistant: it could not execute the basic tasks that the previous one could do, such as routines or orders for home automation. However, Google has spent the last year making Gemini absorb the features of its predecessor. The turning point came at the end of last year, when Gemini Live – the conversational voice mode – finally landed in Spain and in Spanish. Already approaching 2025, Gemini learned a basic function that it was missing: making calls and sending messages without having to unlock the mobile. The last big feature inherited from Assistant, the «Scheduled actions»arrived in June of this year. Google’s plan. At the same time that Gemini was learning the old Assistant tricks, Google has been dismantling the latter, removing useful functions. The objective is more than clear: Gemini is the future and will be everywhere. Now you can act like the “all-seeing” assistant thanks to Project Astra (integrated in Live mode), it is coming to Google Home speakers and its landing on Android Auto is imminent. The last step remains. And that is eliminating the escape route: Google has already consolidated the transition. Gemini is the default assistant on new mobile phones and can be installed on old ones without major impediments. The analysis of the APK of the specialized Android media only confirms that the last step is very simple: eliminate the option to go back. The king is dead, long live the king. Cover image | Composition with Google images and generated with Nano Banana by Pepu Ricca In Xataka | How to create Gemini Gems to have your personalized version of artificial intelligence

How to transcribe WhatsApp or Telegram audios with Gemini

by

Let’s explain to you how to transcribe audios from WhatsApp or Telegram with Geminithe artificial intelligence from Google. WhatsApp and other applications have their own tools for transcribing voice messages, but they are not always accurate, and in fact WhatsApp can leave several words untranscribed due to its limited capacity. Here we are going to go with Google’s AI, since ChatGPT seems to have some problems and not always accept the audio file well. This is a free feature that you will be able to use whenever you want. He prompt It is very easy to use, and so is the process. Transcribe WhatsApp audios in Gemini The first thing you have to do is download voice message in your mobile memory. To do that, select it and choose the share option, and when you do you can choose to do it externally, choose your files application and save it there. You can also save it in the cloudsuch as Google Drive, a service that you can use in Gemini to add files. Now you have to go to Gemini, and attach the audio file that you have downloaded. Here, depending on your mobile or the linked services, when you click on the add elements button you can do it directly from the files or hard drive, or from apps like Google Drive. Once you have added the audio file, you will see that it remains uploaded and attached in the writing field. Now simply write a prompt like “Transcribe this audio”or something similar with which to tell the AI ​​that what you want is the transcription of the message. And that’s it. Only with this you will see that Gemini analyzes the content of the audio file that you have uploaded, and will proceed to transcribe what is said in it. Here, remember that Gemini’s limits for transcribing audio are around 20 MB. In Xataka Basics | Gemini on your old Android: what you need and how to get the most out of it

How to summarize pages with Gemini in Chrome for Android

by

Let’s explain to you how to summarize pages with Gemini in Chrome for Android. This way, if you find a very long article and you don’t feel like it or don’t have time to read it in full, you can ask the artificial intelligence Let me summarize it for you so you can see the key points and go directly to the information it offers. This is something you can do now Gemini It is fully integrated into Android. In the future you will also be able to do it on iOSbut this Gemini feature is not yet available on iPhones. Summarize web pages with Gemini The first thing you have to do is go to the web page you want to summarize in Chrome. So, Press and hold the power button on your phone to summon Gemini on Android. This will open Gemini on top of Chrome, so you can interact with the AI ​​referring to the content you have open on the web. In addition to the writing field, above you will have several options, and you have to press where it says Summarize page in this menu. Just by doing this, in a few seconds Gemini will show you a summary of everything it puts on the website. Here, the important thing is that this summary is overlaid and you have not left Chrome, so whenever you want you can close it and continue browsing normally. In Xataka Basics | Gemini Image Editor: 16 Ways and Tricks to Squeeze Nano-banana with Google’s AI

How to force Gemini to create images of proportions and sizes you want instead of always making them square

by

We are going to explain how to get it Gemini make images with the sizes and proportions that you want. With other alternatives such as ChatGPT This is as easy as telling the horizontalxvertical pixels or telling you an image aspect ratio, but with Geminithe artificial intelligence from Google this seems to fail, and often just makes them all square no matter how much you ask otherwise This is a bug that will surely be corrected over time, but if you need to have control over the proportion of the image you are going to create, we will tell you a little trick with which to force it in an original way. Create images in the proportion you want The first thing you have to do is edit a blank image with the proportion you want using any image editor. You can simply make a blank image and crop it to use a specific size. It could also be a random photo, because in the end it’s just one size template which you will then use in Gemini. Now you have to go to Gemini. When writing the prompt you have to add blank image with size that you have chosen. It will be like putting the canvas on which to later create the image. Then, next to the image add a prompt with this formula: “Replace this image with one that shows (…)”. Here, in the prompt it is important to specify that you want replace that image with a new oneand then describe what you want to appear in the new drawing. By doing this, Gemini will not create the image entirely from scratchbut instead will take as reference the size from which you have uploaded. And then, since you have asked to replace the image, nothing from the previous one will appear, but to avoid problems it is best to have the image blank. This way, you can master one of Gemini’s biggest flaws when creating images, which is that it ignores your size instructions. And remember that you can have several templates of specific sizes. In Xataka Basics | Gemini Image Editor: 16 Ways and Tricks to Squeeze Nano-banana with Google’s AI

If you are a student, you have Gemini Pro free for a year: this is how you can get it

by

If you are a student, Google has just launched a promotion with which you can enjoy Google AI Pro for one year totally free. In addition to being able to use the model Gemini 2.5 Pro whenever you want, with the subscription you can enjoy 2 TB of storage. Its value without promotion is 21.99 euros per month, which is more than 260 euros per year. If you use Gemini in the free version, the model you can use is Gemini 2.5 Flash, faster but also more limited in terms of reasoning capacity. With Gemini 2.5 Pro You can take advantage of the Deep Research mode for more in-depth investigations or make audio summaries, as well as use the imaging with Nano Banana and create videos with I see 3. There’s more, the promotion also comes with 2 TB of storage and more credits to use experimental tools like Whisk and flow to generate images and videos. Requirements to obtain the offer In order to enjoy the Google Gemini promotion, you will have to meet several conditions that we detail below: You must be over 18 years old. Be a university student and your institution offers the Google AI Pro trial. Have a personal Google account. That your Google account has a valid payment method registered. Register before November 3, 2025. How to get the Gemini Pro offer for students If you meet all the requirements, you can register to enjoy the promotion. We tell you how to do it step by step. The first thing you should do is enter the following link https://gemini.google/es/students/ and click on the Get Offer button. If you are not logged in to your Google account, the next step will ask you to do so. Then you will have to fill out the form where you must enter the name of your educational center and your information (in the email do not use the address of your university, use the Google account on which you want to apply the offer). If everything is correct, you will proceed to verification using SheerID. Basically you will have to log in to your university’s platform with the email and username that you have configured on it. You may be asked for proof of registration. You will have to upload the document and click Send. Finally, select “Subscribe to Google AI Pro” and “Student Offer”. When you redeem the offer you will not be charged anything, but we have already seen that in order to subscribe you need to have a valid payment method. If you do not want the subscription to renew and be charged You have two options, wait until the date approaches and cancel it or do it now from this link https://play.google.com/store/account/subscriptions. If you choose the second, you can continue using it until the renewal date. In Xataka | Gemini Image Editor: 16 Ways and Tricks to Squeeze Nano-banana with Google’s AI

How to create Gemini Gems to have your personalized view of artificial intelligence

by

Let’s explain How to create your own Gemini Gemand thus have a personalized version of Google’s artificial intelligence. The Gemini Gems They are like a kind of light and very simplified version of the Artificial Intelligence Agentsnot so complete, but easier to create. The idea of ​​this article is to have a mini guide to understand these personalized versions of Geminiand help you create the first to be able to adapt it to your needs. You will see that they are easier to do than you think, and the options are simple. What are the gems exactly The gems are Personalized versions of Geminithat allow you to use a personalized version of this artificial intelligence assistant. So you can adapt it to perform concrete tasks, play specific roles, or get answers of certain topics that interest you. It is something similar to Chatgpt GPTSbut for Gemini. Gems will allow you to create a version specialized in something concrete of Gemini. Thus, instead of the generic version of the AI ​​you can have one that is centered on the programming, on making a personal tutor or even reviewing your writing. For this, you will simply have to Write instructions telling you what your role and purpose isand from then on all the interactions will start from those rules that you have established. You can even add concrete articles or files to take into account your content in your answers. Although initially the gems were a payment function, currently You can create and use them with a free account from Google with Gemini. However, even being a function that is no longer paying is subject to the general limits of the free account, which means that you can only use the most basic AI model, with a very scarce limit in the use of the advanced model. Another of the limits to be used is in the context window, which is 32,000 tokens or around 50 pages of text, while The file limit for the knowledge base It is only 10. How to create your own gems To create your own Gemini Gems, you have to open the lateral menu of the web or the mobile application. Once inside, click on the option Discover Gems That will appear. This will take you to a screen where you can see a list of gems created by Google itself, and below the section where you have created. Here, click on the + buttonNew gene that will appear to start the process of creating a new one from scratch. This will take you to the screen where you will have to fill in the three necessary fields to create your Gem. You will have to give it a name, instructions and a knowledge base In the event that the latter is necessary. Three fields to define your new gem The first thing you have to do is name your gem. This is the distinctive name it will have, and with which it will appear on your list of gems created. It is recommended that it be a clear and distinctive name. Come on, it is better to call him “expert in SEO writing” than simply “Julián”. Then comes the most complex part, because you will have to Write detailed instructions of the Gem. This is the most important step, because it serves to define the role, tone and rules that this automatism must follow. You have to specify everything you can When you are writing these instructions. These are any of the most important aspects to be defined in the instructions When you are going to create your Gem: Personality: You will have to say what your role is, the character you must interpret and the tone you must use. For example, you can ask you to act as a rigorous but friendly university professor, or an editor of casual content and focused on Reels. Whatever you want, but this personality is important to define it to establish behavior. Objective and rules: It is also also important to specify what the main task of the GEM is, and what are the rules to be used. For example, you can say “Your work is to review the texts to find spelling, grammatical failures and improve the structure”, for example. You can also say things like “Never talk about issues that are not about …” to make it focus on that concrete task. Format: This is something optional, but you will also be able to define the structure of the answers. For example, you can ask that you always start with a summary and then make a list at several points, or whatever you think is necessary. In the end, the question is to define a response structure that is useful and according to the tasks you want to do this customization of Gemini. If you don’t clarify writing the instructionsyou have at your disposal the option to use Gemini to help you write them. For that, write two or three phrases describing the instructions, and then click on the pencil button Use Gemini to rewrite the instructions. By doing so, AI will develop instructions from your phrases, and then you will only have to modify them as you consider necessary. And last place, you have The field of Knowledge Where can you add files. This is something optional, you can simply give your Gem an additional information or context base to reference in chats. These files can upload them from Google Drive or your device. Here, when you upload files keep in mind that They will have priority over general knowledge When you ask the Gem. Come on, that version of Gemini will first look for the answer in those files you have sent, and if you ask you questions that can be answered with them. But if the GEM does not find the answer in its content, then it will resort to Gemini’s general knowledge. Try the Gem before saving it Once you have … Read more

How to create Stickers for WhatsApp with Gemini using these two methods

by

Let’s tell you two methods to make WhatsApp stickers with Geminisomething for which we are going to use two methods with this artificial intelligence. Thus, you can create totally custom sticker from photographs, with which you can express everything you want. Let’s start with the simple method, using Nano Banana in Gemini and a Prompt Next to a photograph. Then we will tell you Another method with which to create a stickers pack using an application for Gemini. In both cases it will be all extremely easy. How to create a stick using Gemini To create a sticker based on a face in Gemini, you just have to Upload a photo and accompany it from a prompt in which you describe what you want. You can use this that we tell you: “Convert this photo into a WhatsApp stick with a pop style Art. The person must be throwing a heart.” You can adapt this stick as you want. The important thing is to mention that it is a WhatsApp stick and say the style. Then, the description of what the person should be doing depends on you, you can adapt it to what you need. Once you have the stick, you can download it. Now, you can use the methods that we have told you to convert any image into sticker directly on WhatsApp. You will only have to upload the image in a chat, with yourself for example, and Choose the option to create sticker in the sharing menu. And that’s it, your custom sticker. Create a stickers pack with Gemini You can also create a sticker pack directly with An application for Gemini. It’s simple, and you just have to go to this link. Once inside, accept the permits that you ask for. You will go to a screen where you can Choose how to add the photobeing able to be by webcam or uploading a photograph. Choose the method you want to upload the image from which to work. After uploading the photo, Choose the style you want to use Among those you have underneath, and click on Create stickers. With this, the application will create a stickers collection immediately. You can lower them one by one, rebuild the one that does not convince you of all, or lower a whole pack. You can try again all the times you want. In Xataka Basics | Gemini Image Editor: 16 forms and tricks to squeeze Nano-Banana with Google’s artificial intelligence

How to convert any person or thing of a photo into a hologram with Gemini and Nano Banana

by

Let’s tell you how convert any object or person of a photo into a hologram. For this we will use Geminithat integrates the free nano model. This allows you to do many things with Gemini’s image editor, such as Create ultra -realistic action dolls From a photo a photo and Many more things. As always, do a task like this with artificial intelligence It does not depend only on the model, but also on Prompt You use, the command with which you ask for it. Therefore, we are going to tell you which one to use and the things you should take into account to perfect it. Turn anything in a photo into a hologram The first thing you have to do is upload a photo to the Gemini writing field, either on the web or on the mobile. Then simply Write the prompt that we tell you belowand click to send everything so that AI does its magic. This is the prompt: “Convert (describe the object or the person to know what you mean) that appears in the image in a 3D hologram of transparent lines.” Here, the most important thing is make the AI ​​understand what object, person or animal you mean When you ask him to make him a hologram. When it is a photo where a distinguishable object appears, like a mobile, then you just have to say the mobile. If two similar things appear, such as two cats or two people, then you will have to give extra indications as you would like a person, such as telling him that he is the person on the right or the cat in the background with dark color. This is already. Only with these indications and leaving the rest of the prompt as Gemini will edit the photo to specifically modify what you have asked. It will not always go well to the firstthat is, you are not afraid to redo the action until it is to your liking. In fact, sometimes the result will be a representation of what is not always corresponding to what it was. For example, if you change a person for a hologram, a silhouette that is not always recognizable will appear. In other words, he sees trying again or tries to add to keep the factions. In Xataka Basics | Gemini Image Editor: 16 forms and tricks to squeeze Nano-Banana with Google’s artificial intelligence

Log In

Forgot password?

Forgot password?

Enter your account data and we will send you a link to reset your password.

Your password reset link appears to be invalid or expired.

Log in

Privacy Policy

Add to Collection

No Collections

Here you'll find all collections you've created before.