To use the Video Podcast feature, you can upload an audio file (such as .mp3 or .wav), provide a URL from platforms like YouTube or TikTok, upload a PDF file, or enter a topic you want to discuss. VisionStory will generate a podcast script with a host and guest if you provide a topic or PDF. 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. When you’re ready, click "Generate" to create your video podcast.
You can upload a podcast audio file and generate a storyboard with AI-powered speakers and shots, but you need a Pro Plan or higher subscription to generate the final video podcast.
No, you don't need advanced editing skills. VisionStory’s AI handles most of the process for you by automatically segmenting your audio, assigning camera shots, and generating a storyboard for your video podcast. You can make adjustments to voice selection and shot types if you wish, but no advanced video editing experience is required.
All video podcasts generated on VisionStory are currently limited to a maximum length of 10 minutes, no matter which subscription plan you have. Please note that longer or more complex videos will consume more credits.
Yes! You can select characters from your existing image library or upload new images to create custom characters. VisionStory’s AI will automatically integrate your chosen characters into the scene, resulting in a realistic and engaging video podcast.
Yes, you can change the voice of each speaker in your original audio. After the storyboard is generated, you can assign different AI voices to each character to match your preferred tone and style.
VisionStory offers three main shot types: single-person close-up, single-person mid-shot, and two-person shot. To change the shot type, click on the relevant segment in the storyboard and choose your preferred shot from the available options. This allows you to focus on one speaker or display both speakers interacting in your video podcast.
Once the storyboard is generated, you cannot replace the characters themselves. However, you can swap the dialogue between the two speakers, so their appearances remain the same but their voices and lines are exchanged.
Don’t worry—if you make a mistake while editing the storyboard, you can make changes at any time before generating the final video. All your edits are saved automatically, so you won’t lose your progress.
Yes, if you don’t have an audio file, you can generate a podcast script from text files, a URL containing your desired content, or simply by providing a podcast topic. VisionStory will use this information to create the dialogue for your video podcast.
Yes, you can upload a custom background scene for your video podcast. VisionStory will automatically place your selected characters into the background you provide, giving you a fully personalized video podcast environment.
You can 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 quickly adjust the video format to suit different platforms.
There is no set limit on the number of video podcasts you can create with VisionStory. However, each video will use credits according to its length and complexity, so your ability to create more podcasts depends on your available credits and subscription plan.
VisionStory does not provide a preview of the final video. However, you can review and edit the storyboard before generating your video. The final output will accurately reflect your storyboard, thanks to VisionStory’s advanced AI, ensuring professional-quality results.
At this time, you cannot manually correct speaker identification errors. This usually happens when two people talk simultaneously in the audio. For best results, use audio where only one person speaks at a time. We are working to improve this feature in future updates.