--- title: 'Cómo crear animaciones ESTILO VOX 100% GRATIS (SIN HERRAMIENTAS DE PAGO)' source: 'https://youtube.com/watch?v=9hLlPMwXIZw' video_id: '9hLlPMwXIZw' date: 2026-08-17 duration_sec: 577 --- # Cómo crear animaciones ESTILO VOX 100% GRATIS (SIN HERRAMIENTAS DE PAGO) > Source: [Cómo crear animaciones ESTILO VOX 100% GRATIS (SIN HERRAMIENTAS DE PAGO)](https://youtube.com/watch?v=9hLlPMwXIZw) ## Summary This video demonstrates a completely free workflow for creating Vox-style documentary animations using Google's Cloud AI, Gemini, and Omniflash. The creator provides a step-by-step guide, from generating a script and image prompts to producing narration and video clips, all without paid tools. ### Key Points - **Introduction to Vox-style documentaries** [00:02] — The video addresses the trend of documentary videos with boxing-style paper cutouts and promises a free method to create them professionally. - **Free tools and master prompt** [00:19] — The creator uses Google's Cloud AI and Gemini, along with Omniflash, and provides a master prompt in the video description for viewers to copy and paste. - **Starting the process with Cloud AI** [01:15] — The process begins by copying the master prompt from a Google Docs document and pasting it into Cloud AI, which then asks for a PDF with source material. - **Selecting a niche and topic** [01:59] — Cloud AI offers seven niches (Crime, History, Money, Disasters, Mysteries, Technology, Sports) or a custom niche, then generates 10 topic ideas. The example uses DB Cooper 1971. - **Generating the script** [02:54] — The user specifies video length (e.g., 30 seconds for demo), and Cloud AI generates a complete script, which can be used for narration or directly for scene extraction. - **Extracting scenes and image prompts** [03:21] — The AI extracts every scene (bit) from the script, creating a prompt.txt file with image prompts for each scene. The example had 14 bits, requiring 14 image prompts. - **Generating a universal video prompt** [04:30] — Cloud AI generates a 10-second universal video prompt, but the creator requests a 5-second version to save time and credits, which is then used for all clips. - **Creating narration with Eleven Labs** [05:11] — The narration script is copied to Eleven Labs, where the user selects the 11P3 model, adds a 'whisper' instruction for a natural tone, and generates the audio. - **Generating images with Saphiwala AI extension** [06:05] — To speed up image generation, the creator uses the Sapiwala AI extension in Chrome, which automatically generates and downloads images from the prompt file. - **Converting images to videos** [07:00] — Each image is uploaded to Google Flow, the universal video prompt is pasted, and the model is set to Omniflash with a 6-second duration and 16:9 aspect ratio to create video clips. - **Editing in CapCut** [08:05] — The final step involves importing the narration and video clips into CapCut, syncing them, adjusting clip lengths, and exporting the final video. ### Conclusion The video provides a complete, free workflow for creating Vox-style documentaries, leveraging AI tools to automate scriptwriting, narration, and video generation, with final editing in CapCut. ## Transcript YouTube by storm right now. Documentary videos with boxing-style paper cutouts that make any subject so interesting you can't stop watching. Here's the question. Without using heavy and expensive software, how do these creators manage to make documentaries with such a professional look? Today I'm going to show you how to do it completely free. Using only Google's Cloud AI and Gemini Omniflash, without paying for a single tool and using a single master prompt that I will leave in the description of this video so you can copy and paste it. So make sure you watch the video until the end to understand the step-by-step process. And by the way, if you want Primo Franco to hold your hand through live video calls , pre-recorded classes so you can go at your own pace, personalized audits of your content where I tell you what to do, what to add, what to remove or what to change so you get results and can live off a completely automated business. I invite you to my new mastermind/digitalempirescommunity. description of this video so you can enter right now and I'll see you inside. Let's begin. First, open my Google Docs document. Yes, this master prompt contains everything you need. Simply copy the entire prompt from beginning to end. Then open Cloud AI in your browser. As you can see, I'm using the free plan. Now paste the master prompt into Cloud AI and press Enter. Cloud AI will ask you for the PDF with the source material. Go back to the Google Docs document, click on engine prompt and a PDF will open. engine prompt and a PDF will open. Download that PDF, return to Cloud AI once more, attach the file, type attach and press enter. Now Cloud will show you seven different niches to choose from: Crime and documentaries, history, money and power, disasters and survival, mysteries and unexplained phenomena, technology and sports. If your niche is not listed here, you can simply write your own custom niche. Now Cloud will tell you, "Respond with a number or a niche." Since I want to create a crime and documentary video, I'm going to write one and press enter. Then, cloud will generate 10 topic ideas related to that niche. You can choose any of those themes. Or if none of them suit your needs, you can simply write your own custom theme. For this example, I'm going to choose to For this example, I'm going to choose to search for DB Cooper 1971. So I'll type one again and press enter. After that, Podi will ask you for the length of your video. A documentary should normally last at least 10 minutes, but just to demonstrate the process, I will set it at 30 seconds. I will type 30 seconds and press enter. As you can see, in just a few seconds Cloud generates a complete 30-second documentary script for you. Now, Cloud AI will display the following message: "Type Voice to generate narration with Eleven Laps or type proceed to go directly to the bits." This means the following. If you type voice, cloud AI will generate a complete script for narration ready to use with eleven laps. If you type proceed, it will skip the narration step and extract every bit of your script. Each bit represents an independent scene, making it easy to create an image prompt for each scene. So first I typed voice and pressed enter and cloud I typed voice and pressed enter and cloud AI generated the entire narration for me. Then I typed proceed and pressed enter. As you can see, Cloud AI extracted every scene or bit from the script. In my case, the script contained 14 bits, which means I will need to create a total of 14 image prompts, one for each bit. Now, Cloud AI will display the following message. Type next to generate the prompt.txt image file for each bit. Simply type next and press enter. A few moments later, cloud AI will generate the image file, or image, however you want to say it, prompt.txt. As you can see, all our image prompts are ready. Next, Cloud AI will tell you, "Generate all the images using the .TXT file. When your images are ready, type 'next' to get the video prompt." Once it finishes generating all the images, type 'next' and press enter. As you can see, Cloud AI generated a 10-second universal video prompt . However, using the 10-second prompt for every clip would make the final video much longer and consume many more Iga credits. So, ask Cloud AI, " Please give me a 5-second universal video prompt ." Then press enter. In a matter of seconds, Cloud AI will generate a 5-second universal video prompt . This is the only universal prompt you'll use with each image to turn it into a video clip. And with that, your video prompt is all set. Now it's time to generate the narration. You're going to go back to Cloud AI and copy the narration script you just created. Then open the 11 Labs website in your browser. Click on "Text to Speech." View the narration script in the box. Text. In the model section, select 11P3. Now, before the first line of your script, simply write an opening parenthesis, the word " whisper," and close it with another parenthesis. This helps give the narration a more natural emotional tone . After that, choose the voice you want to use. When everything is set up, click " generate," and in just a few seconds, your narration will be ready. Listen to it, and if you're happy with the result, download it. November 24, result, download it. November 24, 1971, Portland International Airport . Now it's time to generate the images. First, go back to Cloud AI and download the image prompts file . Then, open Google Flow and image one by one, the whole process could take hours. To speed things up, open Chrome and search for the Sapi wala AI extension. Open it and click "Add to Chrome" to install it. As you can see, I have it installed. Now, go back to Google Flow and click here to open the Sapi wala AI extension. Then, click in this area and upload the The file contains the image prompts. As you can see, it contains a total of 14 image prompts. Now, enable "Auto download" or "Auto download generated images" and disable "Include serial number in file name." Once you've done this, click "Start generation." Now watch the magic happen. The extension will automatically generate each image one by one and save them an image isn't generated or you encounter an error, simply generate that image convert the images into videos. First, go back to Cloud AI and copy the 5-second universal video prompt. Then, open Google Flow and upload your first image. Now, paste the universal video prompt into the prompt box. Next, click "Settings," and if it 's currently set to "Image," change it to "Video." Set the aspect ratio to 16:9 and then select Omniflash as the model. Next, set the duration to 6 seconds and leave the quantity at one. Once everything is set up, press Enter to start the generation. As you can see, the first video has already been generated. While it's processing, repeat the same steps with the rest of your images so that all the videos are generated. Start generating them as well. This way, all your videos will be processed one by one. Now, let me play some of the generated videos so you can see them, or rather, witness the results. Once everything looks good, simply download all the videos. Now it's time to edit the video using CapCut. First, click on " import" and upload the audio we generated with the labs. Then drag the audio to the timeline. Next, click on "import" again and add all your video clips. After that, create a timeline and place each clip in its correct position. Now, slightly increase the audio volume if necessary. Then more precise editing. Listen carefully to the narration and match corresponding part of the audio. If the narration is longer than the clip, . If necessary, you can increase it to double so that it's perfectly synchronized with the narration. Continue adjusting each clip perfectly synchronized with the voice. Once everything is in place... Instead, clips. You can also use additional effects, animations, or other editing tools to make the video look more polished and professional. When you're happy with the final edit, click export the final edit, click export the video. Now let's see the result. International ins. By the way, if you want me to show you how I'm creating, growing, and scaling automated YouTube channels from zero to $3,700 per month in just 30 days, check out this video that's popping up on your screen. And if you want to see how my client earned $4,400 in just 30 days by applying exactly what I teach, check out this other video that's popping up on your screen. Checkout.