How to Create a Talking Video with VisionStory

Dec 15, 2024

Illustration of the talking video creation process

1. Upload or Select a Character

Upload a front-facing photo with clearly visible shoulders and no obstructions for the best lip-sync and facial tracking. If you’ve already uploaded images or want to try VisionStory’s sample library, you can also select an existing character from your collection.

Uploading a character image for video creation

2. Add Your Script or Audio

Next, decide what you’d like your character to say or express:

  • Type Text: Enter your desired script directly into the text field.
  • Import/Record Audio: Upload a pre-recorded audio file or record new audio on the spot.
  • URL Import: Paste a link (e.g., from YouTube or TikTok) to use audio from external sources.

3. Select or Clone a Voice

Once your script or audio is ready, choose the ideal voice:

  • Choose from 200+ AI Voices: Access the Voice Library and filter by language, gender, age, or style. Click the play icon to preview each voice.
  • Clone a Voice (Pro Plan or above): For a custom voice, upload or record a sample. VisionStory will create an AI-based replica for use in your projects.
Selecting or cloning a voice for the character

4. Configure Video Settings

Before generating your video, customise the visuals and output:

  • Quality:
    • Standard (no extra credits required)
    • HD (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 adjust on-screen facial cues (e.g., cheerful, marketing, news). This changes the character’s expression, not the audio’s tone.
  • Green Screen (Pro Plan or above): Enable a solid green background for easy editing or compositing in other video tools.
Configuring video settings for talking videos

5. Generate Your Talking Video

When you’re ready:

  • Preview Audio: Ensure the voice and pacing meet your expectations.
  • Check Credit Usage: Each 15 seconds of video uses 1 credit; HD and green screen options require extra credits.
  • Click “Generate Talking Video”: VisionStory will animate your character, synchronising lip movements with your script or audio.

6. Final Preview & Sharing

Once processing is complete, your video will appear in the Assets section. From here, you can:

  • Preview or Play the final video to review the result.
  • Rename the video title to keep your library organised.
  • Provide Feedback if you’re not satisfied or have suggestions for improvement.
  • Share to X (formerly Twitter) or Facebook for instant 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 create engaging videos where your virtual character speaks with realistic lip-sync and expressive animation. With VisionStory, anyone in Australia can produce captivating, professional-quality talking videos in just minutes!