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. You can also upload a PDF file or enter a topic you’d like to discuss, and VisionStory will generate a podcast script with a host and guest for you. Next, choose a scene and two characters for your podcast. VisionStory will automatically create a storyboard with smart shot selections based on your audio or script, and you can customize the shots, voices, and characters as you like. When you’re ready, click "Generate" to create your video podcast.
Anyone can upload a podcast audio file to generate 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.
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 fine-tune options like voice selection and shot types, but you don’t need any advanced video editing skills.
At this time, all generated video podcasts are capped at 10 minutes in length, no matter which subscription plan you have. Please keep in mind that longer or more complex videos will use more credits.
Yes! You can select characters from your previously uploaded image library or upload brand new ones. VisionStory’s AI will automatically place your chosen characters into the selected scene, creating a realistic and engaging video podcast experience.
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 match the tone and style you want.
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 highlight one speaker or show both speakers interacting.
Once the storyboard is 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.
No problem! As long as you haven’t started the final video generation, you can make changes at any point during the storyboard phase. Your edits are saved automatically, so you don’t need to worry about losing your work.
If you don’t have an existing podcast audio file, you can use tools like Google’s NotebookLM to generate dialogues from text. VisionStory also lets you generate a podcast script from text files, a URL link with the content you want to discuss, or even just by providing the podcast topic.
Yes, you can upload your own custom background scene for your video podcast. VisionStory will place your characters into the scene you upload, giving you a fully personalized setting.
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 adjust the video format for different platforms with just one click.
There’s no set limit to the number of video podcasts you can make, but keep in mind that each video uses credits according to its length and complexity. Your ability to create more podcasts depends on the credits available in your subscription plan.
We don’t provide a preview of the finished video, but you can review and edit the storyboard before generating your video. You can trust that VisionStory’s AI delivers high-quality results, and the final video will accurately reflect your storyboard with professional precision.
At the moment, if the speaker identification is incorrect, there isn’t a way to manually fix it. This usually happens when two people are speaking at once. To help prevent this, try to use audio where only one person is talking at a time. We’re working on improving this feature in future updates.
