Introduction to the Video Podcast Feature

Are you looking for a quick, engaging way to transform your audio podcasts into dynamic visual experiences? Meet the new Video Podcast feature! Now you can turn any two-person audio conversation into an immersive video podcast—with AI-powered scene generation, customizable characters, intelligent shot selection, and more. Here’s a closer look at how it works:

1. Upload or Fetch Your Audio

Start by uploading an audio file (e.g., .mp3, .wav) or pasting a link from YouTube, TikTok, and other supported platforms. Once your file is in the system, you can preview and trim it to focus on the best parts of your conversation, all within our intuitive interface.

2. Select a Scene and Characters

Next, choose a scene to serve as your podcast setting—this can be anything from a cozy studio to a virtual news desk. Then, pick two speaker characters—these can be from the history of images you’ve previously uploaded or you can add entirely new ones.

3. AI-Generated Storyboard

Once you’ve uploaded your audio and selected your characters, AI takes over with smart segmenting and automatic shot allocation:

• Segmenting the audio: The system analyzes the conversation flow, detecting when each speaker talks.
• Automatic shot selection: Each audio snippet is matched with a fitting shot type:
• Single-person close-up to focus on a speaker’s expression
• Single-person mid-shot for a balanced view of your host
• Two-person shot when both speakers interact

These storyboards are created with zero manual intervention—perfect for those who want professional results without expert editing skills.

4. Fine-Tune Your Scenes and Voices

Within the storyboard editor, you can refine each shot to your liking:

• Switch shot types: Go from close-up to mid-shot, or use a two-person shot for both hosts.
• Choose alternative AI voices for each host, if you’d prefer a different tone or style.
• Swap characters: Instantly swap which person is shown in each segment for the best visual flow.

5. One-Click Aspect Ratio Switching

Creating content for multiple platforms? No problem. Easily toggle between 16:9 for a standard landscape view and 9:16 for vertical formats. The scene, characters, and shots all auto-adjust to the new aspect ratio—ensuring your video looks professional across platforms.

6. Generate Your Final Video

Satisfied with the storyboard and the settings? Simply click Generate to produce your complete video podcast. The fast rendering engine brings everything together—your background scene, characters, audio, and camera transitions. In just a few moments, your immersive, AI-driven video podcast is ready to captivate your audience!

Preparing Your Podcast Audio & Key Usage Tips

1. Getting Your Audio

• Don’t have a ready-made podcast file? You can use tools like NotebookLM by Google to generate speech audio from text.
• VisionStory will soon offer a similar service, letting you create a podcast entirely from text on our platform.

2. Speaker Separation Limitations

• Our system currently can’t perfectly separate overlapping voices. If two hosts speak simultaneously, the voice changer feature may not work accurately.
• For best results, use clear audio where only one person speaks at a time.

3. Subscription Requirement

While everyone can upload a podcast audio to generate a storyboard with AI-powered speakers, scenes and shots, the final podcast video generation is available to Pro and above subscribers. If you’re not already a member, consider subscribing to unlock this functionality.

4. Video Length & Credits

• Currently, generated videos are limited to 10 minutes in length, the same limit for all subscription tiers.
• Keep an eye on your credit consumption based on your plan; more complex or longer videos will use additional credits.

Why Choose This Video Podcast Feature?

1. Versatile Use Cases

• Content Creators: Easily add a visual element to your interviews or co-hosted shows.
• Marketing Teams: Promote products or host discussions that captivate audiences on social media.
• Educators & Trainers: Create engaging lesson recaps or remote webinars with a more personable style.

2. AI-Powered Editing

Save hours of manual cutting and shot selection. The algorithms handle the technical heavy lifting for you.

3. Highly Customizable

From selecting backgrounds to refining voices and scene ratios, you remain in control of the final look and feel.

4. Professional Quality, Minimal Effort

Get polished, dynamic video content without needing advanced editing skills or a full video crew.

Transform your two-person conversations into immersive video podcasts with just a few simple steps. Thanks to AI-driven technology, producing professional, visually engaging podcast episodes has never been easier!