Seedance text to video
Seedance Text to Video
No footage needed. Describe the subject, the action, the camera, the light and the sound, and Seedance turns it into a multi-shot clip with audio.
- Prompt only
- Audio from your words
- Several shots per clip
- Up to 1080P
- Price before you render
Prompts and their renders
Each clip lists the model and the exact prompt it was made with. Start from one and change what you like.
“Shot 1: close-up of an old lighthouse keeper in a wet oilskin coat climbing a spiral iron staircase, a swinging lantern lighting his face, rain hammering the windows. Shot 2: wide shot from the sea as the lighthouse beam sweeps across huge storm waves crashing on the rocks, lightning splits the sky. Rolling thunder and howling wind”
Text · 2.0 · 720P · 5s
Use this prompt“Close-up of a young barista with a dark apron behind a café counter, she looks up from the espresso machine, smiles warmly and says "Your usual?". Soft morning light, shallow depth of field, café chatter and an espresso machine hissing in the background”
Text · 2.0 · 720P · 5s
Use this prompt“A street dancer in a yellow hoodie spins and drops into a freeze on a city rooftop at dusk, skyline lights coming on behind her, the camera circles her in one smooth orbit, a punchy hip-hop beat”
Text · 2.0 · 720P · 5s
Use this prompt“A red paper boat drifts down a rain-soaked city gutter at night, neon reflections, the camera follows low and close, soft rain sounds”
Text · 2.0 Fast · 480P · 5s
Use this prompt
Writing for Seedance text to video
In text mode the prompt is the whole brief: Seedance decides the motion, the cuts, the camera and the soundtrack from it. Prompts that read like a director's note work best: who is on screen, what they do, where the camera is and how it moves, the light, and the sounds.
Pick the model by length and budget: 2.0 Fast to try ideas, 2.0 for short finished clips up to 1080P, 2.5 for anything up to 30 seconds. Choose a shape from 21:9 to 9:16; the credits show on the button before you start.
A worked example: "Night market in the rain. A street cook tosses noodles in a smoking wok, the camera starts on the flames and pulls back to show the crowd, neon signs reflect in the puddles, sizzling oil and chatter." One place, one action, one camera move, the light and two sounds. Feelings and backstory don't show on screen, so leave them out.
No idea where to start? Press "Give me an idea" under the prompt box, or use an example on this page: "Use this prompt" copies the exact text it was rendered with.
Seedance 3 AI is independent and not affiliated with or endorsed by ByteDance. Seedance, Dreamina, Jimeng and Doubao are trademarks of their owners.
How to turn a prompt into a Seedance video
Nothing to install and no invite to wait for. Most clips are ready in a few minutes.
- 01
Write the shot
Who is in it, what they do, how the camera moves, the light and what we hear. Or open an example and edit it.
- 02
Add an image or references
Optional: a first or last frame, or reference images, clips and audio for the model to follow.
- 03
Pick a model and render
Choose 2.0 Fast, 2.0 or 2.5, the resolution and the length. The button shows the credits; download the MP4 when it's done.
More ways to create
Seedance 3 AI home
Every Seedance model in one generator, plus Seedance 3 status.
Seedance 3.0
Release status, facts vs rumors, and what to use now.
Seedance 2.5
The newest Seedance: up to 30 s in one clip.
Image to video
Animate a picture, with an optional end frame.
Reference to video
Images, clips and audio steer character, scene and voice.
Text to video questions
Type a prompt in the box at the top, choose the model, length and aspect ratio, and press Generate. Most clips are ready in a few minutes.
Five things, in order: subject, action, camera, light, sound. Concrete nouns and verbs beat adjectives: "a cyclist skids to a stop on wet cobbles" tells the model more than "an exciting scene".
Yes. List the shots in order, or give them time ranges such as "0–4 s … 4–8 s …", and Seedance cuts between them in one clip while keeping the character and the place consistent.
Yes. Put the line in quotes and say who says it, for example: the man at the counter says "Two coffees, please." Seedance generates the voice with the picture.
4 to 15 seconds on Seedance 2.0 and 2.0 Fast, and 4 to 30 seconds on Seedance 2.5.
From 10 credits a second on Seedance 2.0 at 480P, so a 5-second clip is 50 credits. Other models and resolutions cost more; the button shows the exact total.
Yes. The videos you make are yours to use, as long as your prompt doesn't copy someone else's characters, brands or likeness. The terms of service have the details.
Add a short note at the end, such as "no on-screen text, no music". Long lists of exclusions tend to backfire; describing what you want works better.
Turn your prompt into a video
Write one sentence, choose a length and get a video with sound. Your first one is free.
Start creating