--- title: 'How to Create Talking Object and Vegetable Videos with AI for Free - Step by Step' source: 'https://youtube.com/watch?v=L7fxgakCpu8' video_id: 'L7fxgakCpu8' date: 2026-08-03 duration_sec: 419 --- # How to Create Talking Object and Vegetable Videos with AI for Free - Step by Step > Source: [How to Create Talking Object and Vegetable Videos with AI for Free - Step by Step](https://youtube.com/watch?v=L7fxgakCpu8) ## Summary This video tutorial demonstrates how to create videos of talking objects, such as vegetables or fruits, using artificial intelligence. The process is completely free and uses the Grok app for video generation and Gemini with Nano Banana for image creation. The tutorial provides step-by-step instructions for both creating videos from text prompts and animating existing images. ### Key Points - **Introduction to Talking Object Videos** [00:02] — The video teaches how to make videos of talking objects (vegetables, fruits, computers, phones) using AI, completely free and without limits. This trend is getting millions of views and can be integrated into content for a human touch. - **Downloading Grok App** [00:44] — Go to Google Play Store, search for 'Grok', and download the app. It has over 50 million downloads. Sign in with Google, email, or Twitter (X) account. - **Configuring Video Settings** [01:32] — In Grok, click on 'Create videos'. Disable the option 'Automatically create video for image uploads in Animate Photo' to prevent auto-conversion. Set video dimensions (landscape or portrait) and note that free plan defaults to 6 seconds duration and 480p resolution. - **Creating a Video from Text Prompt** [02:12] — Write a detailed prompt describing the object, its appearance, and the speech. Example: 'a cartoon carrot with arms, legs, and wide eyes, standing on kitchen counter, speaking enthusiastically in Egyptian Arabic, says...' Then click the generate arrow. The video generates quickly (96%, 97% complete). - **Improving Resolution and Downloading** [03:06] — Before downloading, click 'Options' and select 'Improve Resolution' to enhance video quality. Then download the video. The result shows the carrot speaking as requested. - **Animating an Image with Gemini** [03:35] — To animate an existing image, use Gemini to create the image with Nano Banana (via 'Thinker' and 'Create Images'). Then go back to Gemini, click the image icon, choose 'Animate Image', upload the image, and write a prompt for the object to speak. - **Generating and Editing Animated Video** [05:03] — After generating, if not satisfied, modify the text and regenerate. Use 'Options' and 'Improve Accuracy' to download. Combine scenes in an editing program; adjust speed to fit longer dialogues. - **Additional Tips and Conclusion** [06:24] — For realistic videos, specify 'realistic video' in the prompt. The app speaks Arabic well after updates. The tutorial encourages trying it and leaving feedback. ### Conclusion The video provides a simple, free method to create engaging talking-object videos using AI tools like Grok and Gemini, with options to customize and improve results. It encourages experimentation and integration into content for viral potential. ## Transcript we'll learn together how to make videos of talking objects, whether it's talking vegetables, talking objects, whether it's talking vegetables, talking fruits, a computer, a phone— talking fruits, a computer, a phone— anything you can turn into a cartoon video that talks with artificial intelligence. We'll do this talks with artificial intelligence. We'll do this completely free and without limits. You can integrate this into your content; for example, I've seen one or two channels where they make things talk and interact with them, giving the video a human touch while still being AI-powered, though not entirely AI-generated. So, let's learn how to make things talk. So, let's learn how to make things talk. This is a trend that's getting millions of views. First, we'll go to the Google Play Store and download an app called "Grok." Just go to the Google Play search bar and type "Grok" in Arabic. It's very simple. Then, the first search result will download the app. I already have it, so I'll start by clicking "Open." Of course, 50 million people have downloaded it. After that, click "Continue with Google" or "Continue with your email," or if you have an account on Twitter (formerly known as X), you can sign up. During this process, let's choose to continue using Google. This will open the email addresses saved on your device. Let's choose, for example, this email address. Then, the screen you see here will open. First, click on "Create videos." A rectangle will appear videos." A rectangle will appear below, prompting you to type. Before you type or do anything else, click on the two lines next to this box. Then, close this option. You'll find it open here: " Automatically create video for image uploads in Automatically create video for image uploads in Animate Photo." Close this option so that if you upload an image, it won't automatically convert it to a video. Now, let's choose the video dimensions. If you want the video in landscape or portrait mode, we'll set it to landscape. The default video duration is six seconds because we'll be using the free plan, and the video resolution is we'll be using the free plan, and the video resolution is 480p. Now, we start writing here very 480p. Now, we start writing here very simply and easily what you want. I'll write it here: I want a video of a carrot in a certain shape. A cartoon character with arms, legs, and wide eyes, standing on the kitchen counter, speaking enthusiastically in Egyptian Arabic, says, "I'm a Egyptian Arabic, says, "I'm a carrot! I improve eyesight and make your skin more beautiful because I'm carrot! I improve eyesight and make your skin more beautiful because I'm full of Vitamin A." Then you select a video, making sure you're on a video. Next, you click here, like this arrow. Then you wait—be careful, it's very fast, one of the fastest AI models. While we're talking, the video is AI models. While we're talking, the video is being generated (96%, 97% complete). Now let's play it: "I improve eyesight and make your skin more beautiful because I'm full of Vitamin A." Great! If you want a girl speaking, you can type in a girl's voice, a boy's voice, or a man's voice, however you like. Before you click download, you click options, then you click "Improve Resolution," options, then you click "Improve Resolution," which will improve the video's resolution. Then you click which will improve the video's resolution. Then you click download the video. The video is almost downloaded. Now download the video. The video is almost downloaded. Now let's see: "I'm a carrot! I improve eyesight and make your skin more beautiful because I'm full of Vitamin A." So, that's how it works. Let's say I want to animate an image. I have a picture and I want it to move. I can go to it to move. I can go to Gemini and create the image using Nano Banana to get a more professional result. Then, instead of the quick option, you choose instead of the quick option, you choose Thinker, click on these two lines, and select Create Images (which is Nano Banana). Click on this arrow to start generating the tomato image (which is cartoon-style). Of course, we're explaining this simply. You can write more professionally, giving you more details. You more professionally, giving you more details. You can describe the image details exactly as you want, or the scene details exactly as you want. But for video purposes, here's the image as you see it. We can save it. Then we go back to save it. Then we go back to Gemini and click on Gemini and click on this icon (the image icon). Then we choose Animate Image. The studio will open. I'll select my image, and then I'll start writing what I want. We wrote it here, like... What you see is that you want the tomato to speak enthusiastically in Egyptian Arabic, in a girl's voice, and say, "I'm a tomato, I protect your heart and boost your immunity because I'm full of antioxidants." Then we click here. If it asks me to confirm my age, I'll choose it, and then I'll click "Continue." Of course, I'll set my age to be over 18. Then it will say, " Video is being created." And as usual, as I told you, it's Video is being created." And as usual, as I told you, it's very fast. Now let's play " very fast. Now let's play " I'm a tomato, I love your heart and boost your immunity because I'm full of antioxidants." If you don't like the result, or if you want to change If you don't like the result, or if you want to change some letters or words—for example, instead of "I protect your heart," I'll say "I some letters or words—for example, instead of "I protect your heart," I'll say "I protect your heart"—then I'll click again, and it will generate protect your heart"—then I'll click again, and it will generate another video. So let's see the another video. So let's see the second result. Okay, the video is ready. We'll play " second result. Okay, the video is ready. We'll play " full of antioxidants." If you like the result, you click on "Options," then " If you like the result, you click on "Options," then " Improve Accuracy," and the video will start downloading. You start making your videos however you want, with the scenes you want, and you combine them want, with the scenes you want, and you combine them on any editing program. For example, if you want a scene to say a lot of words, you can either divide it into two scenes, or if it says the words, you can use the editing program to choose a slower speed, so it starts adjusting the words and making them slower. As a result, instead of, for example, six seconds, you might instead of, for example, six seconds, you might find that the video has reached eight or ten seconds. So that's find that the video has reached eight or ten seconds. So that's the idea in a nutshell, and you can make any video however you want. For example, if you want to make a realistic video, you write here in your app, "I want to make a realistic video, you write here in your app, "I want to make a video, description 1, 3," and it starts making the video for you. It speaks Arabic very well after the latest updates to your app. I want you to try it and tell me if you like it or not? If you are still with me, like the video and leave your opinion in the comments. Peace, mercy and blessings of God be upon you .