To use the Video Podcast feature, simply upload an audio file (such as .mp3 or .wav) or provide a URL from platforms like YouTube or TikTok. You can also upload a PDF file or enter the topic you wish to discuss, and VisionStory will generate a podcast script with a host and guest for you. Next, select a scene and two characters for your podcast. VisionStory will then automatically create a storyboard with smart shot selections based on your audio or script, and you can customise the shots, voices, and characters as per your preference. Once you are happy with the setup, click "Generate" to create your video podcast.
Do I need a subscription to use the Video Podcast feature?
Anyone can upload a podcast audio and generate a storyboard with AI-powered speakers and camera shots. However, to generate the final podcast video, you must have a Pro Plan or higher subscription.
Do I need advanced editing skills to use this feature?
Not at all! VisionStory’s AI handles most of the work for you. The system automatically segments your audio, assigns camera shots, and creates a storyboard for your video podcast. You can make adjustments like choosing voices and shot types, but there’s no need for advanced video editing skills.
Is there a maximum length for video podcasts generated on VisionStory?
At present, all video podcasts generated on VisionStory are limited to a maximum of 10 minutes, no matter which subscription plan you are on. Please keep in mind that longer or more complex videos will consume more credits.
Can I customise the characters used in my video podcast?
Yes! You can select characters from your previously uploaded image library or upload completely new ones. VisionStory’s AI will automatically place these characters into the chosen scene, creating a realistic and engaging video podcast setup.
Can I change the voice of the speakers in the original audio?
Yes, you can change the voice of each speaker in the original audio. After the storyboard is generated, you can choose different AI voices for each character to suit the tone and style you want.
What types of shots are available, and how can I change them?
There are three main types of shots: single-person close-up, single-person mid-shot, and two-person shot. To change the shot, just click on the segment in the storyboard and choose the shot type you want from the available options. You can set the shot to focus on one speaker or show both speakers interacting as per your preference.
Can I change the characters after the storyboard has been generated?
Once the storyboard is generated, you cannot change the characters themselves. However, you can swap the dialogue between the two speakers, so their appearance remains the same but their voices and lines will be exchanged.
What if I make a mistake while editing the storyboard?
No problem! Until you start the final video generation, you can make changes to the storyboard whenever you like. All your edits are saved automatically, so you won’t lose any progress.
Can I create a video podcast using text-based content?
If you do not have a podcast audio file, you can use tools like Google's NotebookLM to generate dialogues from text. VisionStory also allows you to generate a podcast script directly from text files, a URL link containing the content you want to discuss, or even just by providing the podcast topic.
Can I upload my own background scene for the video podcast?
Yes, you can upload your own customised background scene for the video podcast. VisionStory will place your chosen characters into the uploaded scene, giving you a fully personalised setup.
How can I switch between different aspect ratios (16:9 and 9:16)?
You can easily switch between 16:9 (landscape) and 9:16 (portrait) aspect ratios by clicking the toggle button at the top of the storyboard page. This lets you change the video format for different platforms with just one click.
Is there any restriction on the number of video podcasts I can create?
There is no fixed limit on how many video podcasts you can make. However, please keep an eye on your subscription plan’s credit balance, as each video will use credits depending on its length and complexity.
Can I preview the final video before generating it?
No, you cannot preview the final video before generating it. However, you can review and make changes to the storyboard before creating the video. VisionStory’s AI guarantees high-quality output, and the final video will accurately reflect your storyboard.
What should I do if the speaker identification is wrong in the video?
At present, if the speaker identification is incorrect, there is no option to manually fix it. This usually happens when two people are speaking at the same time. To prevent this, please use audio where only one person speaks at a time. We are working on improving this feature in upcoming updates.
