Melon Cut Design

AI video generator: text to video, up to 30 seconds

Write what should happen and Melon Cut's AI video generator makes it. Pick a video model - Kling, Veo, Seedance, Wan, Gemini Omni Flash or Grok Imagine - or let Auto choose, then set the length, up to 30 seconds on the longest models, and the shape, from widescreen 16:9 to vertical 9:16.

longest clip
30 s
shapes, from 21:9 to 9:16
6
credits per started 5 seconds
60
How it works

AI video generator, step by step

  1. Open a video chat

    Start a Video chat and describe the scene: who or what is in it, what happens, the setting, the camera and the mood.

  2. Set the model, length and shape

    Pick a model or leave it on Auto, then choose a length and shape that model offers. The studio shows the credits before you run it.

  3. Watch and download

    Watch the result in the chat and download it, or write a new prompt for another take.

From a sentence to a clip

Text-to-video is the quickest way to get moving pictures for a post, an ad or a website. Describe it the way you would brief a videographer - the subject, the action, the place, the light - and the model makes the clip.

Length and shape, model by model

Clips run from a second or two up to 30 seconds: Kling 4.0, Wan 3.0 and Seedance 2.5 reach 30, Grok Imagine 15 and Gemini Omni Flash 10, while Veo 3.1 makes 4, 6 or 8 seconds. Shapes depend on the model too.

  • 16:9 for YouTube, websites and presentations
  • 9:16 for Reels, TikTok and stories
  • 1:1, 4:3 and 3:4 for feeds and displays
  • 21:9 for wide, cinematic banners

Not sure which model? Use Auto

Auto reads your prompt, picks a video model for it and tells you why. It is a good place to start when you care about the result more than the model's name.

Priced by length

A video uses 60 credits for every started 5 seconds, so a 10-second clip uses 120. With your brand added it is 150 per started 5 seconds, and the studio shows the total before every run.

At a glance

AI video generator: the details

Ways to start
Text, pictures, references, or a video to change
Length
Up to 30 seconds, depending on the model
Shapes
16:9, 9:16, 1:1, 21:9, 4:3, 3:4, or the attachment's shape
Models
Kling 4.0, Wan 3.0, Seedance 2.5, Veo 3.1, Gemini Omni Flash, Grok Imagine, or Auto
Credits
60 per started 5 seconds
FAQ

AI video generator: questions

Can't find your answer? See every question.

How long can the videos be?

Up to 30 seconds with Kling 4.0, Wan 3.0 or Seedance 2.5. Other models make shorter clips; Veo 3.1, for example, makes 4, 6 or 8 seconds.

Can I make vertical videos for Reels and TikTok?

Yes. Choose the 9:16 shape on a model that offers it, or use the Social media video format, which is always 1080 × 1920.

Can I start from a photo instead of text?

Yes. Attach pictures and the first one opens the video, the last one closes it, and up to 8 more act as keyframes in between.

Try it on your next post

Text to video, up to 30 seconds, in the shape you need.