Creator
$19/month
Billed monthly
For solo creators posting every week
500 credits every month
- Up to 250 AI images
- Up to 25 Seedance 2.5 clips
- Up to 1.5 hours of AI voiceover
- Roll over up to 1,000 credits
Text to video AI
Write the shot, get the clip
Describe who is in the shot, what they do, where the camera is, the light and the sound. Seedance 2.5, Kling 4.0, Veo 3.1 and other models turn the words into a clip of up to 30 seconds.
Make this clipPlans from $19 a month
The exact promptKling 4.0 · 8 s · 9:16 · 720p · sound
A line cook in a cramped Hong Kong restaurant kitchen tosses rice in a blackened carbon-steel wok over a roaring gas burner. Camera: handheld at chest height, close and slightly low, with small natural sway and one manual focus pull. 0-3s: he jerks the wok back and the oil catches, a sheet of orange flame climbs up the side of the pan and lights his face and forearms from below. 3-6s: he tosses again, grains of rice and spring onion arc through the flame and land back in the pan, he slaps the ladle against the rim twice. 6-8s: the flame drops, smoke and steam roll up past the stainless-steel hood, the camera drifts left as he reaches for a bowl. Physics: the wok is heavy, his wrist and shoulder take the weight on every toss, sweat on his temple, the apron is stained and creased. Lighting: the flame is the key light, a cold fluorescent tube overhead, greasy tiled wall behind him, fine film grain, low-saturation grade with the fire as the only warm colour. Audio: burner roar, oil crackle, metal on metal, kitchen chatter in Cantonese. No background music. No subtitles.
How do you write a text-to-video prompt?Add one line at a time
One scene, five prompts. Each adds one kind of line, and the clip changes with it.
Seedance 2.5 · 480p draft · 6 s · muted Line 1 · SubjectStart with the subject
A subject alone gets you a fair shot. The model picks what happens, the room, the light and the camera.
A drummer in a black sleeveless top and a white headband plays a huge taiko drum lying flat on a low stand.
Seedance 2.5 · 480p draft · 6 s · muted Line 2 · ActionAdd the action
Say what he does and what it causes. The water gives every hit something to show.
A drummer in a black sleeveless top and a white headband plays a huge taiko drum lying flat on a low stand. He raises both sticks high and brings them down hard again and again, and the water pooled on the drum skin leaps up in bursts of droplets with every hit.
Seedance 2.5 · 480p draft · 6 s · muted Line 3 · LightAdd the place and the light
Name the place, one light source and the look. The backlight turns the spray into sparks.
A drummer in a black sleeveless top and a white headband plays a huge taiko drum lying flat on a low stand. He raises both sticks high and brings them down hard again and again, and the water pooled on the drum skin leaps up in bursts of droplets with every hit. An empty concrete hall at night, one hard spotlight behind him cutting through thick haze, every droplet flashing white against deep black shadow, fine film grain.
Seedance 2.5 · 480p draft · 6 s · muted Line 4 · CameraAdd the camera
Say where the camera sits, how it moves, and what the frame ends on. One move per shot.
A drummer in a black sleeveless top and a white headband plays a huge taiko drum lying flat on a low stand. He raises both sticks high and brings them down hard again and again, and the water pooled on the drum skin leaps up in bursts of droplets with every hit. An empty concrete hall at night, one hard spotlight behind him cutting through thick haze, every droplet flashing white against deep black shadow, fine film grain. Low angle on the drum, the camera pushes in slowly from his whole body to the sticks striking the water and ends on droplets hanging in the backlight.
Seedance 2.5 · 480p draft · 6 s · with sound Line 5 · SoundAdd the sound
Write what you want to hear, and what you don't. The sound is made with the picture.
A drummer in a black sleeveless top and a white headband plays a huge taiko drum lying flat on a low stand. He raises both sticks high and brings them down hard again and again, and the water pooled on the drum skin leaps up in bursts of droplets with every hit. An empty concrete hall at night, one hard spotlight behind him cutting through thick haze, every droplet flashing white against deep black shadow, fine film grain. Low angle on the drum, the camera pushes in slowly from his whole body to the sticks striking the water and ends on droplets hanging in the backlight. Sound: <deep booming hits that echo off the concrete>, <water spattering on the floor>, his mouth stays closed, no other music, no narration.
From text to video in three steps
- 1
Write the shot
Subject, action, place and light, camera, and sound. Start short and add lines.
- 2
Set the clip
Pick a model, a length, a shape such as 9:16 or 16:9, and sound on or off.
- 3
Change one line
Watch the clip, fix the line that missed, and generate again.
Trying many versions? Seedance 2.5 makes a 480p draft first. Finish the one you like in 1080p.
How do you describe camera movement?Four moves, in plain words
Write one move per shot, in the words you would use to a camera operator. Each of these comes from a prompt above.
Handheld
“handheld at chest height, close and slightly low, with small natural sway”
A small human shake. It feels like someone is there filming.
From the wok fire prompt
Orbit
“slowly orbiting him at floor level, about a quarter circle over the whole shot”
The camera circles the subject and shows it from more than one side.
From the breakdancer prompt
Pan
“the operator pans to follow the car”
The camera turns on the spot to follow something across the frame.
From the rally car prompt
Push in
“the camera pushes in slowly from his whole body to the sticks striking the water”
The camera moves toward the subject, from the whole scene to one detail.
From the taiko drummer prompt
Clip not what you pictured?Change the words, then run it again
Too much happens at once
0-3s: … 3-6s: … 6-8s: …
Give each stretch of seconds one action, the way the prompts at the top do.
Music you didn't ask for
No background music.
Say it at the end. Veo 3.1 and Kling 3.0 also have a field for what to leave out.
Words burned into the picture
No subtitles.
If the scene has no signs or labels, ask for no text and no logos too.
Movement looks weightless
Physics: the wok is heavy, his wrist and shoulder take the weight on every toss
Say what is heavy, wet or loose, and how it moves.
It looks like stock footage
Lighting: the flame is the key light, a cold fluorescent tube overhead
Name where the light comes from, its colour, and the grade.
The face or product has to match
Start from a photoWords can't copy a real face or label. Use the photo as the first frame, or make a Persona for the same person in every clip. Your first Persona is free.
The story needs more than one shot
Split it into shotsKling 3.0 and Kling 4.0 make up to six shots in one run, with one prompt per shot. You can also join clips on the Studio timeline.
Which text to video model?Start on Seedance 2.5
It is the default for a text prompt. Switch when the shot needs something it doesn't do.
Seedance 2.5
The default. Strong at people talking on camera, with speech and lip sync.
- 4 to 30 s
- Draft to 1080p
- Sound on or off
Kling 4.0
One take of up to 30 seconds, always with sound. It made the three clips at the top.
- 3 to 30 s
- 720p or 1080p
- Sound always on
Kling 3.0
Up to six shots in one run, and a field for what to leave out.
- 3 to 15 s
- Standard or Pro
- Sound on or off
Veo 3.1
Short shots in up to 4K, wide or vertical.
- 4, 6 or 8 s
- Up to 4K
- Sound on or off
Simple pricing that scales with you.
Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.
Pro
Most popular$49/month
Billed monthly
For creators posting daily across channels
1,300 credits every month
- Up to 650 AI images
- Up to 65 Seedance 2.5 clips
- Up to 4 hours of AI voiceover
- Roll over up to 2,600 credits
Studio
$99/month
Billed monthly
For brands and production teams
2,700 credits every month
- Up to 1,350 AI images
- Up to 135 Seedance 2.5 clips
- Up to 9 hours of AI voiceover
- Roll over up to 5,400 credits
Scale
$199/month
Billed monthly
For agencies running always-on content
5,500 credits every month
- Up to 2,750 AI images
- Up to 275 Seedance 2.5 clips
- Up to 18 hours of AI voiceover
- Roll over up to 11,000 credits
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights
Want checkout, comparison tables, or a custom volume? See the full pricing page
Before you writeCommon questions
Text to video AI turns a written description into a video clip. You describe the subject, what happens, the camera, the light and the sound, and a video model makes the clip. On Sceneform you can pick Seedance 2.5, Kling 4.0, Veo 3.1 and other models.
Open the video generator and write the shot: who is in it, what they do, where the camera is, the light and the sound. Pick a model, a length, a shape and whether you want sound. Generate, watch the clip, and change the one line that missed.
Plans start at $19 a month, and every plan can make video from text.
It depends on the model, the length and the quality. A 5-second Seedance 2.5 clip with sound costs 25 credits as a 480p draft, 55 at 720p and 134 at 1080p. An 8-second Kling 4.0 clip at 720p, like the ones at the top of this page, costs 60. The $19 Creator plan has 500 credits a month. You see the exact cost before you generate.
Models follow concrete words best. Give each stretch of seconds one action, name the camera move and the light, and say what to leave out, such as "No background music. No subtitles." For an exact face or product, start from a photo with image to video.
One take runs up to 30 seconds on Seedance 2.5 and Kling 4.0, up to 15 seconds on Kling 3.0, and 4, 6 or 8 seconds on Veo 3.1. Kling 3.0 and Kling 4.0 can also make up to six shots in one run.
Yes. Seedance 2.5, Kling 4.0, Kling 3.0 and Veo 3.1 make sound with the picture. Write it in the prompt: effects, ambience, and spoken lines in quotes. Kling 4.0 always adds sound. The others let you turn it off.
A video model makes one shot at a time, so write each shot as its own prompt. For a narrated video from a topic or a link, Storybook writes the narration and illustrates each part.
No, that is a different tool. Add text to video puts captions and titles on a clip you already have.
Yes. Every paid plan includes commercial use, and videos export without a watermark.
Your shot is written.
Action
Plans start at $19 a month.