To use the Video Podcast feature, just upload an audio file (such as .mp3 or .wav) or provide a URL from platforms like YouTube or TikTok. Next, select a scene and two characters for your podcast. VisionStory will automatically create a storyboard with smart shot selections based on your audio, and you can customise the shots, voices, and characters as you like. When you’re happy with everything, click "Generate" to create your video podcast.
Do I need a subscription to use the Video Podcast feature?
Anyone can upload a podcast audio file to create a storyboard with AI-powered speakers and camera shots, but you'll need a Pro Plan or higher subscription to generate the final podcast video.
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 splits your audio, assigns camera shots, and creates a storyboard for your video podcast. You can tweak things like voice selection and shot types if you like, but there’s no need for any advanced video editing skills.
Is there a limit to how long a generated video podcast can be?
At the moment, all video podcasts you create are capped at 10 minutes, no matter which subscription plan you’re on. Keep in mind that longer or more detailed videos will use up 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 brand new ones. VisionStory’s AI will automatically place these characters into your 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 for 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 do I change them?
There are three main shot types: single-person close-up, single-person mid-shot, and two-person shot. To change a shot, just click on the segment in the storyboard and choose your preferred shot type from the available options. You can adjust the shot to focus on one speaker or show both speakers interacting.
Can I change the characters after generating the storyboard?
Once the storyboard has been generated, you can’t 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 happens if I make a mistake while editing the storyboard?
No worries! As long as you haven’t started the final video generation, you can make changes at any time during the storyboard stage. Your edits are saved automatically, so you won’t lose your progress.
Can I create a video podcast from text-based content?
If you don’t have an existing podcast audio file, you can use tools like Google’s NotebookLM to generate dialogues from text. VisionStory will soon introduce a feature that lets you create video podcasts directly from text within the platform.
Can I upload my own background scene for a video podcast?
Yes, you can upload your own custom background scene for your video podcast. VisionStory will place your chosen characters into the scene you’ve uploaded, giving you a fully personalised setting.
How do I switch between different aspect ratios (16:9 vs 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 a limit to how many video podcasts I can make?
There’s no set limit on the number of video podcasts you can create, but keep in mind that each video will use credits according to its length and complexity, as per your subscription plan.
Can I preview the final video before generating it?
We don’t provide a preview of the finished video, but you can review and make changes to the storyboard before generating your video. VisionStory’s AI delivers high-quality results, and the final video will accurately reflect your storyboard with professional precision.
What should I do if the speakers are identified incorrectly in my video?
At the moment, if the speakers are identified incorrectly, there’s no way to manually fix it. This usually happens when two people talk at once. To minimise this, we recommend using audio where only one person speaks at a time. We’re working on improving this feature in future updates.
