How to Create a Talking Video with VisionStory
Dec 15, 2024

1. Upload or Choose a Character
Upload a front-facing photo with clearly visible shoulders to ensure smooth lip movement and facial tracking. If you’ve already uploaded images or want to experiment with VisionStory’s sample library, you can also select an existing character from your available collection.

2. Add Your Script or Audio
Next, decide what your character will say or convey:
- Type Text: Enter your desired dialogue directly in the text field.
- Import/Record Audio: Upload a pre-recorded file or record new audio on the spot.
- URL Import: Paste a link (e.g., from YouTube or TikTok) to incorporate audio from external sources.
3. Select or Clone a Voice
Once you’ve set up your script or audio, it’s time to pick the perfect voice:
- Choose from 200+ AI Voices: Access the Voice Library, where you can filter by language, gender, age, and style. Click the play icon to preview each voice.
- Clone a Voice (Pro Plan or higher): For a custom voice, upload or record sample audio. VisionStory creates an AI-based replica of that voice for you to use in multiple projects.

4. Configure Video Settings
Before finalizing your video, tailor the visuals and output:
- Quality:
- Standard (no extra credits)
- HD (Pro Plan or above, additional credits may apply)
- Aspect Ratio: 9:16 (portrait), 16:9 (landscape), or 1:1 (square), depending on where you plan to share.
- Facial Expressions: Use the “Emotion" selector to adjust on-screen facial cues (e.g., cheerful, marketing, news). This controls the character’s expression, not the audio’s tone.
- Green Screen (Pro Plan or higher): Enable a solid green background if you wish to composite the character into other scenes later.

5. Generate Your Talking Video
When everything is set:
- Preview Audio: Check that the voice and pacing match your expectations.
- Check Credit Usage: Each 15 seconds of video costs 1 credit; HD and green screen incur extra credits.
- Click “Generate Talking Video”: VisionStory will animate your character, synchronizing lip movements with the chosen script or audio.
6. Final Preview & Sharing
After processing, your video appears in the Assets section. From this page, you can:
- Preview or Play the final video to see how it turned out.
- Rename the title of video to keep your library organized.
- Provide Feedback if you’re not satisfied or want to offer suggestions for improvement.
- Share to X or Facebook directly for quick social posting.
- Copy Link to share your video on other platforms.
- Download the MP4 file for local storage or embedding on websites.
- Delete the video if you no longer need it.
By following these steps, you’ll be able to craft engaging videos where your virtual performer speaks with realistic lip-sync and expressive animations. With VisionStory, anyone can create a captivating on-screen presence in just minutes!