Create a video from text with AI
Describe who is in the frame, what happens, and how the camera moves. Rapir sends the prompt to a suitable model and creates a clip without filming or source footage.
- Input
- A natural-language description
- Scene
- Subject, action, camera, and light
- Format
- 16:9, 9:16, and other ratios
How it works
- 1
Write the prompt
Describe the subject, action, environment, lighting, and camera movement.
- 2
Configure the clip
Pick an available model, ratio, duration, and resolution.
- 3
Start the render
Rapir creates the video and keeps it with the prompt in your chat history.
Benefits
- Write prompts in natural language
- Multiple text-to-video models in one service
- Formats for ads, feeds, and vertical clips
- See the estimated cost before rendering
Models in Rapir
How to write a video prompt
A useful prompt answers four questions: who or what is in the frame, what happens, where the camera is, and which visual mood you need. Specific motion usually reduces random changes.
- Subject: person, product, animal, or environment.
- Action: what changes during the clip.
- Camera: framing, angle, and movement.
- Mood: lighting, color, pace, and style.
When text-to-video works best
Use it for ad concepts, intros, short scenes, idea visualization, and social content. If a specific person or product must remain exact, start with image-to-video instead.
FAQ
No. Text-to-video starts from a written description; an image is only needed for image-to-video workflows.
See also
Ready to try?
Open Rapir and get it done in a single chat — with starter credits and no watermarks.
Start for free