# How to create AI YouTube Shorts in MINUTES with HeyGen Video Agent! (No Editing Needed) Source: https://qvantx.com/insights/how-to-create-ai-youtube-shorts-in-minutes-with-heygen-video-agent-no/ Author: Ani Björkström — QvantX Sweden AB, Stockholm Published: 2025-10-18 Updated: 2026-09-20 Video: https://www.youtube.com/watch?v=TC1Ea6v-Jsg (6 min) Topic: AI Tools License: free to quote and cite with attribution to https://qvantx.com --- _AI TOOLS_ ## Can HeyGen's Video Agent turn one prompt into a finished YouTube Short? #### Key takeaways - HeyGen's Video Agent converts a single text prompt into a full production plan — topic, audience, script, avatar, voice, B-roll, music and captions — in one to two minutes. - You revise the plan by chatting with the agent ("please disable captions", no music) rather than editing settings screens; the agent updates the plan and shows it again before rendering. - Video length runs from 15 seconds up to 3 minutes; 60 seconds in 9:16 portrait is the sweet spot for YouTube Shorts, and the final render took about five minutes. HeyGen's Video Agent is a prompt-to-video workflow: you describe what you want, the agent plans the whole production, and you approve or correct it in plain language. Ani Björkström, a tech consultant based in Stockholm, demonstrated the flow end to end by producing a YouTube Short explaining Sora 2, with the only manual work being two chat messages to adjust the plan. ### How do you start a video in the Video Agent? Log into HeyGen, open Video Agent, and use the plus button to attach material — either "choose from assets" for videos and pictures already saved in HeyGen, or "upload from device" for anything stored locally on your computer. Then add an avatar: public avatars are open to everyone, while your own avatars sit under "my avatars", where each avatar can carry many different looks — one shown in the tutorial had 83. Set the duration (auto, or fixed lengths up to 3 minutes), pick the 9:16 or 16:9 ratio, and paste your prompt; in this case the prompt itself was drafted in ChatGPT first. ### What does the agent's plan actually include? After a minute or two of thinking, the agent returns a structured setup covering every production decision, not just the script. Reviewing this plan is the real control point in the workflow, because everything downstream is generated from it. | Plan item | Example from the tutorial | |---|---| | Topic and audience | Sora 2 explainer for viewers interested in AI video | | Length and orientation | 60 seconds, portrait (9:16) | | Script plan and target language | Generated from the prompt | | Avatar and voice | The creator's own saved avatar and voice | | B-roll | Footage illustrating Sora 2's features | | Music and captions | Both on by default; both switched off by chat request | ### How do you change settings before rendering? You type the change into the chat. In the tutorial the instructions were "please disable captions" and to remove the music — reasonable choices for a tutorial-style video — and the agent regenerated the plan within moments, showing captions disabled and the music theme set to "no music". Once the plan looks right, you type "proceed" and rendering begins; the agent estimated five minutes for the finished video. ### What happens after the video is created? The finished Short is ready to distribute directly from HeyGen. You can click share to send a link, or click download to save the file and publish it yourself on YouTube Shorts or TikTok. The demo delivered a complete Sora 2 overview — its diffusion-transformer approach, the VPN and invite-code workaround for European users, and a note on ethical use of likeness and consent — all generated from one prompt. #### FAQ **How long can a Video Agent video be?** You can let the agent decide based on your prompt, or fix the length at options such as 15 seconds, 30 seconds or 60 seconds, up to a maximum of 3 minutes. **Do I have to write the script myself?** No. The agent builds the script plan from your prompt. In the tutorial the prompt itself was generated in ChatGPT and pasted in. **Can I use my own face and voice?** Yes. Avatars you have created appear under "my avatars", each with multiple looks, and the plan uses your saved avatar and voice. ## Full video transcript [0:01] My name is Annie. I'm a tech consultant based in Stockholm. And in this tutorial, I will show you how to use Hygien's new video agent to create YouTube shorts or videos that you can publish in Tik Tok. So you will log into Hygien and then you will click on video agent and here you can see these windows and if you click on the plus button you can choose from assets or you can upload from device. And when you click on choose from assets, this means that you can choose from different videos or pictures that you already created and saved in hygien. And the other button where it says upload from device, then you will be uploading from your local device from your computer. For example, from your downloads catalog or if you have any other cataloges. [0:49] So anything that is locally saved in your computer is available in this section. Then if you click on add button here you can choose your avatar and let's choose an avatar for me and you can see that here are public avatars which means that everyone can use those avatars and under my avatars and in hygien how it works that you create an avatar and then on that avatar you can create different looks. So you can see that on this avatar I have 83 looks and if I click on that I will scroll down and choose one of my early looks. You can see that I created a lot of different avatars. And this of course makes video creation a lot easier. [1:34] Then you have this auto button here. You will define how long your video will be. So you can decide how long your video would be based on your prompt or you can choose and define that it needs to be 15 seconds, 30 seconds, 62 minutes or maximum 3 minutes. And I will choose 60 seconds. I think that's sweet spot for YouTube shorts. And then you also will decide your ratio. It can be either 916 or 169. And then here you will just write your prompt. for me. I have already asked you to create a short prompt for me and I will just copy that from chat GP and I will come back and I will put here. Yes. [2:19] And then after that we will just hit enter button and the agent will start to think. It will right now take one or two minutes and will create a setup where it will say for example what is the prompt and what is the resolution in which language is this video and so on. So here it says topic and then audience and then music also there is a music and you can see video length and you can see video orientation that is portrait in this case script plan and then target language avatar. Okay, that's my provide avatar voice and then you have some B-roll. I immediately illustrate the features of SA 2 and then captions are also enabled. So what you will do in this stage if there is something that you want to change for example maybe you don't want to have captions enabled. [3:11] So I will write please disable captions and if there is something else that you want to change you can do that in here. I don't want to have a music because this is a tutorial. So, I will hit enter. And then what the agent will do, it will go back and it will try to update all of those settings that I asked the agent to update and we'll create a new plan. Normally, this goes quite quickly, you can see. And let's see if it did what I asked for. The captions are disabled, which is great. And then let's see if music is also disabled. Yes. And that music theme is no music. Then I think this looks fine. So I will just enter proceed. And you can see it will take 5 minutes to create this video. [3:59] So then I will stop in here and I will come back to you once the video is created. Video was created. Let's check it out together. Sora 2 generates short video clips from text prompts offering impressive realism and controllability. Key features: detailed scenes with characters, backgrounds, and realistic motion. Achieve cinematic styles, select aspect ratios, and create an AI version of yourself with consent. Sora 2 uses diffusion transformer technology like Dolly, adapted for motion. It refineses video by removing noise, ensuring consistent highquality output. For European users, Sora 2 requires a workound. [4:48] It's officially available in the US and Canada. Use a VPN to connect via a US or Canadian server. Then visit openai.com/sora. An invite code is essential even with a VPN as Sora 2 is invite only. Sora 2 is powerful but prioritize ethical use especially regarding likeness and consent. Yeah. And then if you want to share it, you can either click on share and share the link or you can click on download and download the YouTube short or this video to publish in YouTube. Yeah. So that was it. I hope you liked it. Have a good day. Bye.