Language: English

Text to video: write a scene, get a video clip

Text to video turns a written description into a video clip. In shuut's video tool you can start from text only, with no picture or footage needed.

Several models handle text to video in shuut. They differ in whether they speak your lines, how they treat sound and how long a single clip can run.

Open the tool on shuut

Models for this

ModelMade byPriceLowest priceLength
Seedance 2.5ByteDance26 credits per second12 credits per second4–30 seconds
Veo 3.1Google44 credits per second22 credits per second4 seconds, 6 seconds, & 8 seconds
Kling 4.0Kuaishou18 credits per second18 credits per second3–30 seconds
Seedance 2.0ByteDance17 credits per second8 credits per second4–15 seconds
MiniMax H3MiniMax10 credits per second10 credits per second4–15 seconds
Wan 3.0Alibaba11 credits per second6 credits per second2–30 seconds
Grok Imagine Video 1.5xAI16 credits per second9 credits per second1–15 seconds
Omni 1.2 FlashGoogle8 credits per second3 credits per second3–15 seconds
HappyHorse 1.1Alibaba16 credits per second8 credits per second3–15 seconds

Prices are in credits (1 credit = US$0.01) and are deducted from your shuut balance per use. You see the exact price before each generation.

How text to video works in shuut

Open the video tool and pick a model from the list.

Describe the scene in the prompt: who is in it, where it happens, what moves and how the camera behaves.

To have a character say something, put the line in quotation marks and pick a model that speaks quoted lines.

On models with a sound switch, turn sound on or off before you press “Generate”.

For more than one shot, Director Studio turns a scene description into a storyboard and then into a film.

Which models do text to video and how they differ

Seedance 2.5, Kling 4.0, Veo 3.1, Veo 3.1 Fast and Omni 1.2 Flash speak lines you put in quotation marks.

Kling 4.0 (made by Kuaishou), Grok Imagine Video 1.5, HappyHorse 1.1, Omni 1.2 Flash, MiniMax H3 Highspeed and H3 Lite always add sound to the clip.

Seedance, Veo 3.1 and Wan 3.0 let you choose whether the clip has sound. MiniMax H3 itself makes silent video.

Seedance 2.5, Kling 4.0 and Wan 3.0 can make a long single clip, so they suit scenes that need more time.

Veo 3.1 is Google's video model. Veo 3.1 is the highest-quality Veo, at 1080p with dialogue and ambient sound. Veo 3.1 Fast is faster and cheaper and still makes dialogue and sound effects.

Seedance 2.5 is made by ByteDance and goes up to 1080p. Seedance 2.5 Flash is faster and cheaper, at 480p and 720p.

Tips for a text to video prompt

Write the spoken words exactly as they should sound, inside quotation marks.

Seedance 2.5 also speaks Korean lines.

If you want a silent clip, choose MiniMax H3, or turn sound off on Seedance, Veo 3.1 or Wan 3.0.

Check the “Length” column in the table on this page before you pick a model for a longer scene.

Seedance 2.5 and Veo 3.1 also accept a first scene and an end scene, if you later want to steer the clip with pictures.

If real people appear in the video, check whether the place you post it needs an AI-generated label.

How to make a text to video clip in shuut

  1. Open the video tool in shuut.
  2. Pick a model, for example Seedance 2.5, Kling 4.0 or Veo 3.1.
  3. Describe the scene and put any spoken lines in quotation marks.
  4. Set sound on or off if the model offers the choice.
  5. Press “Generate” to get your video clip.

Frequently asked questions

Which text to video model can speak my dialogue?
Seedance 2.5, Kling 4.0, Veo 3.1, Veo 3.1 Fast and Omni 1.2 Flash speak lines you put in quotation marks. Seedance 2.5 also speaks Korean.
How long can a text to video clip be?
Each model's clip lengths are listed in the “Length” column of the table on this page. Seedance 2.5, Kling 4.0 and Wan 3.0 make the longest single clips.
Veo 3.1 or Veo 3.1 Fast: which one suits my clip?
Veo 3.1 is the highest-quality Veo, at 1080p with dialogue and ambient sound. Veo 3.1 Fast is faster and cheaper and still makes dialogue and sound effects.
Can a text to video clip come out without sound?
Yes. MiniMax H3 makes silent video, and Seedance, Veo 3.1 and Wan 3.0 let you turn sound off.
How much does text to video cost in shuut?
Every model shows its price as a quote before you press “Generate”. For Veo 3.1 the price differs with and without sound.

What you can make

Open the tool on shuut

Updated November 17, 2026

Before you start

You pay per result, with a quote before you press “Generate”; subscriptions are optional.

Motion shots, captions and resizing are free once you sign up.

Section 9 of the Terms covers commercial use; scope varies by model and agreement, and checking rights, ad rules and AI labels is up to you.

shuut isn't affiliated with the model makers.

Prices · Terms