Video & Task
To make a video, upload a clear front-facing image that shows the shoulders and has no obstructions. Then, either type the text you want the avatar to say or upload/record your own audio. Select a voice from 1,000+ options in 88 languages, click Generate, and your talking video will be created quickly.
Every registered user gets 10 free credits plus a weekly visit bonus (the amount depends on your plan tier). The free credits are enough for a short talking video of roughly 30 seconds. Once all the free credits have been used, a subscription is required. We believe this gives you plenty of time to fall in love with our product.
Please visit the assets page (https://app.visionstory.ai/assets) and click on the video you’re not satisfied with. On the video details page, there is a feedback button. If you submit your feedback, we will review it, and you may receive a credit refund for that task. You can also email us with your feedback.
The maximum video length you can generate depends on your subscription plan. Free users can create videos up to 30 seconds long. The Pro plan allows videos up to 3 minutes, the Advanced plan up to 10 minutes, and the Ultra plan supports videos up to 20 minutes in length.
VisionStory supports the following aspect ratios: 9:16 (portrait), 16:9 (landscape), and 1:1 (square).
To remove the watermark from your videos, you will need to subscribe to one of our paid plans.
You can turn on the Green Screen feature during generation. A green screen video is a video where the background is filled with a solid green colour, making it easier to isolate the person in the foreground. You can import this video into editing tools such as CapCut to replace the green background with another image or video of your choice. You need to subscribe to at least the Pro Plan to use the Green Screen feature. Using the Green Screen feature costs 1 extra credit per 15 seconds of video (about 4 credits per minute).
An HD video is a video with a 720p resolution, while an FHD video has a 1080p resolution. You can create HD or FHD videos by selecting the desired resolution during the video generation process. To use the HD feature, you must have at least a Pro Plan subscription, and to generate FHD videos, you need to be subscribed to the Advanced Plan or higher.
You can control the emotions and expressions of the person in the video by choosing from a range of options such as cheerful, angry, marketing, news, or singing. These are tailored for different scenarios, enabling you to customise the video to suit your specific requirements.
No, the videos you create are only visible to you. However, if you choose to share the generated video, others will be able to view it via the share link.
You can delete a video by navigating to the video details page and clicking the delete button. Please note that deletion is permanent and cannot be undone.
The number of tasks you can submit simultaneously depends on your subscription plan: free users can submit up to 2 tasks, Pro plan users can submit 4 tasks, Advanced plan users can submit 6 tasks, and Ultra plan users can submit up to 10 tasks at once.
While we do our best to provide sufficient computing power for all users, your task may be queued if resources are limited during periods of high demand. Tasks are prioritised according to subscription level, with higher-tier plans receiving higher priority in the queue.
An AI-generated title is automatically assigned to each video you create. If you wish to change it, go to the assets page (https://app.visionstory.ai/assets) and click on your video. On the video details page, you’ll find a rename button. When you download the video, the file will be named using your chosen title and the creation date for easy organisation.
To enhance the quality of your generated video, upload a clear, front-facing, high-resolution image with visible shoulders and no obstructions. Use high-quality audio for speech, and choose suitable emotions and expressions for your character. Lip sync generally works best with smiling expressions. If you are not satisfied with the results, you can submit feedback using the button on the video details page, and you may be eligible for a credit refund for that task.
In most cases, this issue is related to your own device or connection. Please check that your internet connection is stable. We recommend using popular browsers such as Chrome or Safari to access our website and download videos, as some less common browsers may have compatibility issues. If the problem continues, please contact us by email for further assistance.
Yes, VisionStory provides an API for video generation. You can find the documentation here: https://app.visionstory.ai/openapi/docs
VisionStory offers 720p, 1080p, and 2K video resolutions; higher resolutions are available on higher plan tiers — see the pricing page for your plan’s limit. Per 15-second block, a 720p video costs 4 credits, a 1080p video costs 6 credits, and a 2K video costs 14 credits. Any partial block is rounded up to a full block.
Our native talking-video model is V-Character, which generates talking videos with expressive faces, accurate lip-sync, and dynamic hand and body movements. We also offer external cinematic video models — Kling, Seedance, and Wan — which are billed per second of output and cost more than native generation.
To download your video, go to the Assets page (https://app.visionstory.ai/assets), select the video you wish to download, and click the download button on the video details page.
