Write a sentence. Get a finished short video.
No camera, no stock footage, no editing timeline. Your words become generated scenes with matching sound, delivered as one ready-to-post MP4.
How it works.
- 01
Write your brief
Describe who or what is on screen, what happens, where it happens, and how it should sound.
- 02
Choose shape and quality
Pick vertical 9:16 for Shorts, Reels, and TikTok, or landscape 16:9 for YouTube and websites. Then pick 480p, 720p, or 1080p.
- 03
Download the MP4
In a few minutes the finished video appears in My videos, ready to download.
What you get.
Footage from words
Every frame is generated from your brief, so you can show places, creatures, and moments you could never film.
Sound that fits
Ambience, music, and speech are created with the picture, not added later. A quoted line in your brief gets spoken.
Vertical or landscape
Make 9:16 videos for phones or 16:9 videos for desktop players from the same kind of brief.
Photos as references
Add up to four photos to guide characters, products, or style. One photo on its own can be animated.
Captions on request
Auto captions follow the spoken words, timed so each one appears as it is said.
How to write text that turns into good video
Write like a shot list, not an essay. A strong brief has one subject, one action, a setting, and a light source: "an old fisherman mends a net on a dock at dawn, fog on the water." Fifteen seconds holds one or two beats, so cut anything that reads like a second scene. Describe sound as well as picture, such as gulls, a creaking dock, or a far-off bell, because the audio is generated from your words too. If you want someone to speak, quote the line exactly. Captions come from spoken words, so dialogue is the way to get text on screen. Adjectives about mood help more than technical terms. When a result misses, keep what worked and change one phrase at a time.
- An astronaut plants a flag on the moon, then the flag starts slowly spinning like a pinwheel.
- Close-up of an old letter curling at the edges on a candlelit desk, rain tapping the window.
- Wide shot of a lighthouse at dusk as a storm rolls in, waves crashing, low thunder rumbling.
- A narrator in a cozy study turns to the camera and says: 'Nobody knows who built this door.'
Questions, answered.
What is text to video AI?
It is a model that creates video from a written description. You type what should happen, and it generates the footage and the sound together. Here, each brief becomes one finished 15-second MP4 you can download.
How long can a text to video clip be?
Each paid video is 15 seconds. Your free first video is a 5-second 480p clip, so you can test a brief before you buy anything. Longer pieces need several clips joined in your own editor.
Can I mix text with my own images?
Yes. Add up to four photos alongside your brief to guide the look of people, products, or places. If you add a single photo, the model can animate that image directly.
How much does text to video cost?
A 15-second 720p video costs 40 credits. The Hobby plan is $19.99 a month for 250 credits, about six HD videos. If a generation fails, the credits are refunded automatically.