To create a video, simply upload a front-facing image where the shoulders are visible and there are no obstructions. Then, either type the text you want the avatar to speak or upload/record your own audio. Select from over 200 voices in 30+ languages, click on Generate, and your talking video will be ready within minutes.
Is video generation free?
Every registered user receives 10 free credits, which are enough to create videos totalling up to 2 minutes and 30 seconds. Once you use up all your free credits, you will need to subscribe to continue generating videos. We believe this free trial period gives you enough time to experience and enjoy our product.
Where can I give feedback if I am not happy with the generated video results? Can I get my credits refunded?
On the video details page, you will find a feedback button. If you submit your feedback about unsatisfactory results, we will review it and you may receive a credit refund for that task. You can also email us with your feedback.
What is the maximum video length I can generate on VisionStory?
The maximum video length you can generate depends on your subscription plan. The Free Plan supports up to 15 seconds, the Lite Plan allows up to 1 minute, the Pro Plan allows up to 3 minutes, and the Advanced Plan and higher let you create videos up to 10 minutes long.
Which aspect ratios are available for video creation on VisionStory?
VisionStory supports 9:16 (portrait), 16:9 (landscape), and 1:1 (square) aspect ratios for video creation.
How can I remove the watermark from my videos?
To remove the watermark from your videos, you need to subscribe to one of our paid plans.
What is the Green Screen feature and how can I use it?
You can enable the Green Screen feature while generating your video. A Green Screen video has a solid green background, which makes it easy to separate the person in the foreground. You can then use editing tools like CapCut to replace the green background with any image or video you prefer. To use the Green Screen feature, you need to be subscribed to at least the Pro Plan. This feature costs 1 extra credit per minute of video, with a minimum charge of 1 credit.
What is an HD video, FHD video, and how do I use them?
An HD video is a video with 720p resolution, while an FHD video has 1080p resolution. You can select either HD or FHD when generating your video by choosing the desired resolution option. To use the HD feature, you need to subscribe to at least the Pro Plan. For FHD videos, you must have an Advanced Plan or higher.
How can I control the emotions or expressions of the person in the video?
You can control the emotions and expressions of the person in the video by choosing from different options like cheerful, angry, marketing, news, or singing. These options are designed for various situations, so you can customise the video as per your specific requirements.
Will the videos I create be visible to others?
No, only you can see the videos you create. However, if you share the generated video using the share link, others will be able to view it.
How can I delete a video I have created?
You can delete a video by visiting the video detail page and clicking on the delete button. Please note that once deleted, this action cannot be undone.
How many tasks can I submit at the same time?
The number of tasks you can submit at once depends on your subscription plan: Free users can submit up to 2 tasks, Lite plan users can submit 3 tasks, Pro plan users can submit 4 tasks, and Advanced plan or higher users can submit 6 tasks simultaneously.
Why is my task in a queue?
We do our best to provide enough computing power for all users, but sometimes your task may be placed in a queue if there are too many requests at the same time. Tasks are processed based on priority, so users with higher-tier subscription plans will have their tasks handled first.
Can I change the title of my video?
Yes, the AI will automatically generate a title for each video you create, but you can rename it on the video details page. When you download the file, it will be named as per your chosen video title along with the creation date, making it easy to organise your files.
How can I improve the quality of my generated video?
To get better results for your generated video, make sure you 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 usually works best with smiling expressions. If you are not satisfied with the result, you can use the feedback button on the video details page to share your feedback, and you may get a credit refund for that task.
Why am I unable to download my video?
In most cases, this issue is related to your end. Please check that your internet connection is stable. We recommend using popular browsers like Chrome or Safari to access our website and download videos, as some less common browsers may have compatibility issues. If you still face problems, please contact us by email for further assistance.
Does VisionStory offer an API for video generation?
Yes, VisionStory provides an API for video generation. You can find the API documentation here: https://www.visionstory.ai/openapi/docs
What video resolutions are available on VisionStory, and how many credits does each require?
VisionStory supports video resolutions of 480p and 720p. By default, videos are generated in 480p, which costs 1 credit for every 15 seconds of video (with a minimum of 1 credit per video). If you want to generate videos in HD (720p), you need to be on the Pro Plan or above, and it will cost 1 extra credit for every 15 seconds (total 2 credits per 15 seconds). Currently, 1080p resolution is not available. Credits are deducted based on the video length, and any video shorter than 15 seconds will still consume 1 credit.
Which video generation models are currently available, and how are they different?
We currently offer two video generation models: V-Talk and V-Character Preview. V-Talk is mainly used for creating talking videos with realistic facial expressions and accurate lip sync. V-Character Preview, on the other hand, includes hand movements and more dynamic body actions, making the videos even more lively.
