AI Text to Video
Say who or what is in it, where, what happens and how the camera moves. You can describe several shots.
0/400
Need an idea?
Make a video from text with AI
Describe a clip and Dromana makes it — no photo, no editing. Say who or what is in it, where it happens, what happens and how the camera moves; describe several shots and it can cut between them.
Step 1
Describe the clip
Two or three sentences are plenty: “a golden retriever puppy bounds through autumn leaves, the camera low and following it in slow motion”.
Step 2
Pick a shape and length
Vertical 9:16 or wide 16:9. Dromana Ultra makes 5-, 8- or 10-second clips; other models go up to 30 seconds.
Step 3
Generate and share
Sign in when you press Generate. Download the MP4 or share it in one tap.
Tips for better results
- Name the subject, the place, the action and the camera move — in that order.
- Light and time of day do a lot: “golden hour”, “neon at night”, “soft studio light”.
- For several shots, write them out: “Shot 1: wide… Shot 2: close-up…”.
- Want a real face or product in it? Switch to With a photo.
FAQ
Is text to video free?
Yes, to start. New accounts get 100 free credits once — enough for a 5-second video and a few images — and every paid plan starts with a 7-day free trial. Free results carry a small Dromana watermark; paid plans don’t.
How much does one clip cost?
A 5-second Dromana Ultra clip is 70 credits. Every model shows its price before you generate.
Can I make a clip with several shots?
Yes. Describe the shots in order and a multi-shot model cuts between them, keeping the same characters.
Can I put myself in it?
Yes — switch to With a photo, or pick a look from the library, and your photo is used as the start.
What can’t I make?
Anything explicit, and anything involving minors or real people without their consent. See the safety guidelines.
Also try Make an image from text instead, or see pricing.