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.
Models for this
| Model | Made by | Price | Lowest price | Length |
|---|---|---|---|---|
| Seedance 2.5 | ByteDance | 26 credits per second | 12 credits per second | 4–30 seconds |
| Veo 3.1 | 44 credits per second | 22 credits per second | 4 seconds, 6 seconds, & 8 seconds | |
| Kling 4.0 | Kuaishou | 18 credits per second | 18 credits per second | 3–30 seconds |
| Seedance 2.0 | ByteDance | 17 credits per second | 8 credits per second | 4–15 seconds |
| MiniMax H3 | MiniMax | 10 credits per second | 10 credits per second | 4–15 seconds |
| Wan 3.0 | Alibaba | 11 credits per second | 6 credits per second | 2–30 seconds |
| Grok Imagine Video 1.5 | xAI | 16 credits per second | 9 credits per second | 1–15 seconds |
| Omni 1.2 Flash | 8 credits per second | 3 credits per second | 3–15 seconds | |
| HappyHorse 1.1 | Alibaba | 16 credits per second | 8 credits per second | 3–15 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
- Open the video tool in shuut.
- Pick a model, for example Seedance 2.5, Kling 4.0 or Veo 3.1.
- Describe the scene and put any spoken lines in quotation marks.
- Set sound on or off if the model offers the choice.
- 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
- Image to video AI: turn a photo into a moving clip
- AI shorts maker: vertical clips, captions and resizing in shuut
- AI video upscaler: enlarge clips and photos to 4K
- AI lip sync video with Kling Lip Sync
- AI talking avatar video from a photo and a voice
- AI UGC video from a presenter photo, a product photo and a script
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.