[00:03] artificial intelligence in Arabic. I'll show you how AI can create images, sounds, or even videos for you to use in design projects, content creation, or anything else you can think of. So, let's get straight to the point. Open a
[00:20] browser on your computer or phone, like Google Chrome, and go to a website called bhutia.
[00:32] all the AI ​​tools in one place. The great thing about it is that you don't need advanced skills. You can use it in Arabic right now. Just click on the English language icon at the top to change it to Arabic, and the website will be in Arabic. You can even type in Arabic. The best thing about
[00:48] it is that it opens on both phones and computers, so you can access it wherever you want because it opens in your browser. Let's start with the easiest thing you can do: audio. The audio creation tool is right there; if you look, you'll find it. It's very clear because it has a
[01:04] sound icon. That's it—create audio.  Click on it, and here you start typing the text you want to use for the voiceover. So here I am, typing the text. After typing, I can easily choose the voiceover artist. Of course, the site automatically understood what language I was using and gave me Arabic speakers who speak with the same
[01:19] voice. So here you can listen to the voices and choose the person you want. Content can be a turning point. Did you know that content can be a turning point in your life? I liked Sufyan's voice. Did you know that creating content can be a turning point in your life? I liked Sufyan's voice.
[01:31] Did you know that creating content can be a turning point? Okay, I'll take his voice. This is how I create the voiceover, and here, in just 10 seconds, I'll have the file ready. So, that's it. The
[01:43] easiest thing to do is create the voiceover. Artificial intelligence today is no longer a luxury develop 100%. The voiceover is now available; I can download it, edit it, delete it, or do anything I want. This was the first tool, the voiceover tool, but
[01:58] you can also create the voiceover.  It works without anything, without a face, and you can add voice to a face. This is a digital character tool that creates a voice for you, but the voice is with a face. So, for example, you can put yourself in front of a voice, and your voice will come out with the voice. You can
[02:13] talk and move like me, or for example, you can hold this girl and write the text you want, or you can raise your voice. If you raise your voice, you record it with a microphone, and she will speak exactly like you. She will even move and say anything. So, I have the text; it's
[02:29] there. I chose the character. Here, I choose the language: English or Arabic (of course, Arabic). Then I choose the voiceover. I have many Arabic or English voices for males and females. I listen to the voices. This girl's voice is set up like Maryam's. Did you know that the voiceover creation is
[02:44] very excellent? Maryam's voice is for this girl. I create a video, and now I have a video of this girl, whom I have named Maryam, saying the words I wrote. So, this is how you can add voice to a face. Or a voice without a face, and you're free to use it. This feature might take a minute or two to create the
[02:59] video, but I don't have to wait. I can go back to the main screen and just click up, and it will start working on the video. But I go to the library. This is the video I'm making of the girl's video, example, "How are you, my friends?" [Music]
[03:12] Today I want to teach you how to write cartoon stories using artificial intelligence. This is how I create voices with and without faces. This was the first feature, creating voices. But now let's move on to creating images. You can do work with the image
[03:28] creation feature, and you have the image editor feature. The image editor feature lets you comment on an image; you give it an image and take an image. But with image creation, you give it the text and take the image. So here, I just tell you to explain what you want to say. You don't give it anything except your text. So now I'm going to
[03:43] try speaking to it in very basic language. I'll tell it, "A man is working on a laptop."  In a modern cafe with natural lighting and a realistic style—I won't even mention the lighting, I'll just say a man working on a laptop in a cafe. These things aren't really considered cafes, but the camera will
[03:58] fill in the details itself. Is the man Arab, foreign, American, Australian? Who is he? Is he working on a laptop? What laptop? Is he in a modern cafe? In which country? What's the lighting like? What's the atmosphere like?
[04:11] If you don't explain these things, the camera will create them. So let's do something basic. I'll choose the image dimensions now. Images have dimensions—a picture is vertical, a picture is horizontal, a square picture. I'll choose 169, which is horizontal. I'll also choose 1K resolution. 1K is excellent; you
[04:27] don't need 2K or 4K. Now, I'll create the image, and that's where the camera starts to render the image for me. The five or six words I mentioned—that's the image. It depicts a man working on a laptop in a modern cafe. It does everything, but I don't want this person; I don't want this angle.  I wanted the
[04:43] camera zoom; I wanted the camera closer to him, but it didn't turn out the way I imagined. However, it did what I wanted. Now I'm going to try something with more detail. I'll tell it this: I 'll show it a high-quality, realistic image of an Arab man in his thirties. I'll mention his background and age,
[04:59] then I'll show it him in front of a modern desk with an open laptop. I'll even tell it what I want on the laptop—I'll tell it to display an AI interface, the lighting, the background, all the details. Of course, I can even add the camera angle now. I can tell it, for example, to make the camera (what's called a close-up shot)
[05:14] camera angle now. I can tell it, for example, to make the camera (what's called a close-up shot) the camera, and the image appears. The Arab man in his thirties is on the laptop, right in front of him. And the close-up image is exactly as I requested. Everything is as I
[05:29] asked. The great thing about this feature is that you can edit, retry, and redo. Reusing features improves them. They clarify that you're editing an image. You tell it, for example, that you want to edit this specific image. You don't rewrite the text here; you type it. You press the edit feature, and then you can
[05:45] edit only this image, or animate it, convert it to a video, or upload it. But here, pay attention to the difference between the first and second images. This is the difference in AI, and it's not about being an expert. The point is knowing how to explain the details. This is what
[06:01] I explained in the details below; it's what's called the Prompt, and it usually contains everything you need to convey to AI. So, that was the image creation feature. But now let's try the image editing feature, which is the image editor. Here, you're not required to type the text.
[06:17] To edit an image, the first thing you need to do is give it the image. So, you either choose an image from your library, or you upload it. I have two ready-made images; I could even take the image and put it on the site, but by pressing upload, I'll take this girl's image, and I can
[06:31] even upload a command.  The image editing feature allows you to edit two images simultaneously and merge them. I added a picture of the girl, and I could add another image as well. I uploaded the image of the girl and the product image, and now it tells the program what to do with the two images. The great thing about this image editing feature is that
[06:46] you have all the details ready. You don't need to explain what the product is or who the girl is because everything is already there. I can just give it a very simple description. I gave it the two images and told it to have the veiled Saudi Arabian woman holding the product in a
[07:01] suitable, realistic, and advertising way, without adding any extra text or changing the basic product details. This is more than enough for the image editing feature because it has all the details; you just need the text. I click on "Create," and now it starts working on the image. Here's the result:
[07:17] the girl is holding the product, the same girl, in the style I wanted. Even the text didn't get messed up; the word "Brad Radah" is still there. Here's where I made a mistake the first time I did this. I forgot to specify the image dimensions, so it was set to square for automatic conversion.
[07:32] However, I immediately changed it back to 9x16, which is portrait. Now, I have the image ready, and I can, as always, optimize the upload. These are things I want to animate, to convert to a video. This is the third feature: converting an image to a video. It's done by clicking "Animate." It was already on the
[07:51] I'm going to do it directly from the feature. I'll tell it to have a female voice speaking and promoting the Prada lipstick product in Arabic. The specific details are important; the language is Arabic. Although it's clear the girl is Arab, I have to specify that it's in
[08:07] Arabic so he doesn't mess up the AI ​​and start doing whatever he wants. But here, I let him speak as he pleased. I told him to have the female voice speaking and promoting the product; I didn't even specify what the words were. I just have the voice creation feature enabled, and now... Clean 2.6 and 6 Pro Clean are well-
[08:21] organized and have sound. I'll use 3.1 and Fast this time because they also have sound. Now I'll choose the video settings, which include sound generation. I want it to be ATP (full HD), eight seconds long, and I want it to be 9x16 (portrait). After I've explained the settings and what I
[08:37] want, here's the image uploaded. I also chose the model type because there are many types. If you don't know them, stick to the ones the website provides. But if you do know them, you'll know which one you want. My website provides. But if you do know them, you'll know which one you want. My
[08:51] comparison videos or try them yourself to really understand how to work with each one. Now it's ready, like creating videos. Now the video creation feature might take some time. Before I start working on the video, I can open the website in New Tab because it's a website, and then use
[09:06] another feature, like creating a video, which is called Text to Video.  I was just using a picture-to-video converter—that's what it's called here—and I converted a girl's picture into a video. But this time, I'm going to make a text-to-video converter, which is without a picture, just the words. So, I
[09:21] paused, the writer of the text asked for a green-eyed alien with huge eyes, wearing sunglasses. I said, " Where am I sitting? In the front seat of a white Hyundai taxi." I said, "There are cracks in the dashboard." I said, " Even the alien sticks its head out." Then I said, "What does it say next?" I said, "This is its speech." I told it what accent,
[09:37] voice, language, and finally, what it does after speaking. So, I told it all the details of how I want the video to be complete. Then I told it what the resolution, duration, and all the details. Then, I just pressed "Create," and that's when it started converting the text into a video. And the video is ready!
[09:52] video. And the video is ready! It gives you a bold, innocent, and attractive look. [Music] Personally, I can't do without it. Okay, the video is considered very excellent. I can use it for advertising, use it personally, edit the text, or recreate it. That was the
[10:06] conversion feature.  Image to video: This was the original image, and I converted it to the girl ready too. Two medium milk, my dear Two medium milk, my dear [laughs].
[10:25] details are very nice. Even the hijab looks very realistic. Of course, there's a small mistake in the video; the word "taxi" didn't come out correctly. Maybe because the video started and the word "taxi" wasn't visible, even though it was. But the video started and the word "taxi" wasn't visible, even though it was. But
[10:40] mistakes happen in AI. You know, AI hasn't reached perfection yet, but for it to reach this level is something very excellent. So, since I've now made a video, images, and audio, I can of course upload anything I want and go back to the main screen. I told you all these are AI features, and there are still
[10:55] other features like creating subtitles, which adds the text that appears below, or you have the video editor feature, which allows you to edit the videos. So, I'm here now to upload the video. I have the file with images, audio, and videos, but I'm holding it.  I put the video I
[11:10] want to start with here. The site takes it, and I can even change its dimensions. All these features are available on the site, but here, as soon as I create, reset, and continue, the site immediately finishes creating the video for me, like an editing program. I have all the features: images, subtitles, audio, I can add anything I
[11:26] want. This is useful if you want to make simple edits, like combining two videos, adding subtitles, or adding audio. For example, if I want to add audio or an image, I just drag and drop it onto the site, and the site takes it directly. So
[11:40] now you can use AI to create images, audio, videos, content, and anything else you want with artificial intelligence. You can try Bth.ai now and tell me what you think
[11:52] try Bth.ai now and tell me what you think in the comments.