A step-by-step guide to generating professional AI videos from text descriptions using Kensa.

How to Create AI Video from Text Prompts

Creating videos from text prompts is the most popular way to use AI video generation. This guide walks you through the entire process.

Prerequisites

A Kensa account (free signup available)
Credits in your account (new users get free credits)

Detailed Steps

Step 1: Write Your Prompt

The prompt is the most important part of the process. A good prompt should include:

Subject: What is in the scene?
Action: What is happening?
Style: What aesthetic are you going for?
Technical: Camera angle, lighting, quality

Be specific about the scene, style, lighting, and camera movement. For example:

A golden retriever running through a sunlit meadow, cinematic slow motion, warm lighting.

Step 2: Choose an AI Model

Model	Best For	Duration
Sora 2	Cinematic scenes	10-15s
Veo 3.1	Short clips	4-8s
Kling 3	Realistic video with audio	5-15s
Seedance 1.5 Pro	Flexible quality control	4-12s

Step 3: Configure Video Settings

Start with these recommended settings for beginners:

Duration: 10 seconds
Aspect Ratio: 16:9
Quality: Standard

Set your preferred duration (5-15 seconds), aspect ratio (16:9 for landscape, 9:16 for social media), and quality level. Shorter durations generally produce higher quality results.

Step 4: Generate and Download

Click Generate and wait for your video. Generation typically takes 2-5 minutes. Once complete, you can preview, download, or share your video directly.

After clicking generate, your video enters a queue. You will receive a notification when it is ready.

Pro Tips

Iterate: Your first attempt may not be perfect. Refine your prompt and try again.
Use templates: Browse our template gallery for inspiration.
Start short: Begin with 5-second videos to test your prompts quickly.