To use the Video Podcast feature, simply upload an audio file (e.g., .mp3, .wav) or provide a URL from platforms like YouTube or TikTok, then choose a scene and two characters for your podcast. You can also upload a pdf file or input the topic you want to talk about, and VisionStory will generate a podcast script with host and guest for you. Then VisionStory will automatically generate a storyboard with smart shot selections based on your audio or script, and you can customize the shots, voices, and characters. Once you’re satisfied, click "Generate" to create your video podcast.
Everyone can upload a podcast audio to generate Storyboard with AI-powered speakers and shots, however you need to have a Pro Plan or higher subscription to generate the final podcast video.
Not at all! VisionStory’s AI does most of the work for you. The system automatically segments your audio, assigns camera shots, and generates a storyboard for your video podcast. You can fine-tune things like voice selection and shot types, but you don’t need any advanced video editing skills.
Currently, all generated video podcasts are limited to 10 minutes in length, regardless of your subscription tier. Be mindful of your credit consumption as longer or more complex videos will use additional credits.
Yes! You can choose characters from your previously uploaded image library or upload entirely new ones. VisionStory's AI will automatically place these characters into the selected scene, creating a realistic and engaging video podcast setup.
Yes, you can change the voice of each speaker in the original audio. Once the storyboard is generated, you can select different AI voices for each character to match the tone and style you prefer.
There are three main shot types: single-person close-up, single-person mid-shot, and two-person shot. To change a shot, simply click on the segment in the storyboard and select the desired shot type from the available options. You can adjust the shot to focus on one speaker or show both speakers interacting.
While you can't change the characters themselves after the storyboard is generated, you can swap the dialogue between the two speakers. This means their appearance stays the same, but their voices and dialogue will be switched.
No worries! As long as you haven't entered the final video generation stage, you can make adjustments at any time during the storyboard phase. Your changes are saved automatically, so you don’t have to worry about losing your progress.
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 provice the ability to generate podcast script from text files, a url link with contents you want to talk about, or even just the podcast topic.
Yes, you can upload your own custom background scene for the video podcast. VisionStory will place your characters into the uploaded scene, allowing for 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 allows you to adjust the video format for different platforms with one click.
There is no specific limit to the number of video podcasts you can create, but be mindful of your subscription plan's credit usage. Each video will consume credits based on its length and complexity.
We don’t offer a preview of the final video, but you can review and adjust the storyboard before generating the video. Rest assured, VisionStory’s AI ensures high-quality results, and the final video will match your storyboard with professional accuracy.
Currently, if the speaker identification is incorrect, there is no way to manually adjust it. This issue typically arises when two people speak at the same time. To avoid this, we recommend using audio where only one speaker is talking at a time. We are actively working on improving this feature in future updates.
