Skip to content
Text to Video

Text to video in minutes

KivoHeadShots turns a written description into a 5 or 10 second video, with sound if you want it, in landscape, portrait or square format. It costs from 24 credits a run, and new accounts get 10 free credits.

Try Text to Video

From 24 credits per run

What you need to turn text into a video

  • Describe the scene

Example: turn text into a video

Made with Text to Video on this site. Your results depend on your description and settings.

Description typed

“A paper boat floating along a rain-filled street during the monsoon, close-up at water level, raindrops rippling the water, soft reflections of shop lights”

After: Landscape, 5 seconds, with sound (with sound)

Why use our text to video tool

Write a scene and get a 5- or 10-second video in landscape, vertical or square, with optional generated sound.

  • Cinematic quality from a description
  • Three shapes
  • Optional sound

How to turn text into a video

  1. 1

    Describe your video, or upload the image, video or audio it starts from.

  2. 2

    Choose length, shape and sound.

  3. 3

    Watch and download the finished clip. Videos take a few minutes.

Your uploads are deleted as soon as the run finishes, and never used to train AI. How we protect your photos

Questions about the text to video tool

Can it show text or logos?
AI video models aren't reliable with text. Add titles and logos in your editor afterwards.
How do I write a good scene description?
Say who or what is in the shot, what happens, where it is and how the camera moves, for example “a street food stall in Delhi at night, steam rising, slow push-in”. One clear action works better than several.
How long does a video take?
Usually 2–6 minutes. You can leave the page: the video appears in your history when it's ready.
What if a video fails?
If the AI can't finish a job, your credits are refunded automatically.

More ai video tools