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

1. Upload or Select a Character
Upload a clear, front-facing photo with visible shoulders and no obstructions for the best facial animation and lip-sync accuracy. If you have already uploaded images or want to try VisionStory’s sample characters, simply choose an existing character from your library.

2. Add Your Script or Audio
Decide what your character will say or express:
- Type Text: Enter your desired dialogue directly into the text field for AI-powered speech synthesis.
- Import or Record Audio: Upload a pre-recorded audio file or record new audio directly within VisionStory.
- URL Import: Paste a link from platforms like YouTube or TikTok to extract and use audio from external sources.
3. Select or Clone a Voice
Choose the ideal voice for your video:
- Choose from 200+ AI Voices: Browse the Voice Library and filter by language, gender, age, and style. Preview each voice to find the perfect match for your project.
- Clone a Voice (Pro Plan or higher): Create a custom AI voice by uploading or recording sample audio. VisionStory will generate a personalized voice clone for use in your videos.

4. Configure Video Settings
Customize your video before generating:
- Quality:
- Standard (no extra credits required)
- HD (720p, Pro Plan or above; additional credits apply)
- Aspect Ratio: Choose from 9:16 (portrait), 16:9 (landscape), or 1:1 (square) to suit your sharing platform.
- Facial Expressions: Use the “Emotion” selector to set the character’s on-screen expression (e.g., cheerful, marketing, news, singing). This affects visual expression, not the audio tone.
- Green Screen (Pro Plan or higher): Enable a solid green background for easy background replacement in post-production.

5. Generate Your Talking Video
Once your settings are ready:
- Preview Audio: Listen to the generated speech to ensure the voice and pacing meet your expectations.
- Check Credit Usage: Each 15 seconds of video uses 1 credit. HD and green screen features require additional credits.
- Click “Generate Talking Video”: VisionStory animates your character, synchronizing lip movements and facial expressions with your script or audio.
6. Review, Share, and Manage Your Video
After processing, your video will appear in the Assets section. Here you can:
- Preview or play the final video to review the result.
- Rename the video title for better organization.
- Provide Feedback if you’re not satisfied or want to suggest improvements—eligible for credit refunds if the result is unsatisfactory.
- Share directly to X (Twitter) or Facebook for instant social media posting.
- Copy Link to share your video across other platforms.
- Download the MP4 file for local storage or embedding on your website.
- Delete the video if you no longer need it (note: deletion is permanent).
By following these steps, you can easily create professional-quality talking videos with realistic lip-sync and expressive animations. VisionStory empowers marketers, content creators, and storytellers to bring ideas to life—no advanced editing skills required!