Test the idea first
Explore with a shorter duration or lower resolution. Check whether the action reads clearly before spending credits on a longer take.
Wan 3.0 Text to Video
Wan 3.0 Text to Video turns scene descriptions into up to 30-second 1080p clips with sound. Set your camera movement and output options, then create online.
Model
0 / 20,000
Aspect ratio
Resolution
Duration
5 seconds2s30s
Sign in to create
Output Preview
Example video
Ready to generate
Turn Text into a 30-Second Wan 3.0 Video
Wan 3.0 Text to Video is an online generator that builds moving scenes from written descriptions. With Wan 3.0, your text sets the subject, surroundings, action, and mood. A quiet coastal morning or a busy night market can begin with a few clear sentences.
Give the scene a beginning, a change, and an ending. Add one camera movement and describe the ambient sound. The suggested prompt shows how to ask for a simple three-part sequence.
- Duration
- Up to 30s
- Resolution
- 1080p
- Sound
- With audio
Paste your prompt into the generator above, then choose 30s and 1080p in the settings.
Suggested prompt
A morning on the water
A small fishing boat crosses a calm bay at sunrise. Pale gold light falls across the water, with mist along the distant cliffs. Let the scene unfold at this approximate pace:
- 0–10s
Establish the scene
Open wide on the quiet bay as the boat enters from the left. Keep the camera steady.
- 10–20s
Follow the movement
Slowly track alongside the boat as its wake catches the sunlight. Let the cliffs move into view.
- 20–30s
Let the moment settle
Ease into a wider view as the boat moves toward the horizon. End on the gentle ripples.
Audio: soft water against the hull, a low boat engine, and distant seabirds. No dialogue or music.
Original prompt example. Timing suggests a pace; the generated sequence may vary.
How Wan 3.0 Text to Video Works
Move from an idea to a first take in three steps. Keep the first attempt focused on one clear action.
Step 1
Describe a scene
Name the subject, what happens, and where. Add lighting and a camera direction that supports the action.A fishing boat crosses a quiet bay at sunrise, with a slow sideways camera move and gentle waves.
Step 2
Choose your settings
Pick Standard or Prime, an aspect ratio, a resolution, and a duration. Review the credit estimate before generating.Step 3
Generate and review
Sign in and generate. Review motion, framing, and sound, then change one detail for the next take.
For a broader walkthrough, follow the Wan 3.0 creation guide.
Create 1080p Video from a Text Prompt
Wan 3.0 Text to Video offers 480p, 720p, and 1080p output. Select resolution in the controls; adding ‘1080p’ to your prompt alone does not set the output size.
Choose the delivery format
Select 1080p for the highest available resolution here. Choose the aspect ratio for where the video will be shown.
Compare the available credit packs on the pricing page.
Add Camera Motion to Your Scene
A useful Wan 3.0 camera movement prompt says where the camera starts and how it moves. Choose one main movement instead of asking for several competing moves.
Slow push-in
Move closer to emphasize a small action, such as steam rising from a cup.
Sideways tracking
Travel beside a moving subject. Specify its direction so the camera and action work together.
Gentle pullback
Begin close, then move away to reveal the surroundings. Allow time for the wider setting to become readable.
Generate Video with Native Audio
Wan 3.0 Text to Video requests include audio automatically. Describe the sound in your prompt; there is no separate audio switch to enable.
Separate the main sound from the background: a kettle whistle over a quiet kitchen hum, or footsteps above distant traffic. Match the description to the visible action, then listen to the completed clip.
“Audio: a soft kettle whistle in the foreground, quiet room ambience behind it. No dialogue or music.”
Wan 3.0 Text-to-Video Examples
Watch a real Wan 3.0 Text to Video result with its recorded prompt and settings. The creative cards below offer additional prompt ideas; their suggested settings are separate from the generated example.
Generated example
Wan 3.0 Text to Video example: coffee by the window
This generated clip shows a beige coffee cup with steam beside a sunlit window on a wooden table. Play the video to inspect the movement and listen to the generated audio; the prompt below records the directions used for this take.
- Standard
- 480p
- 5s
- 16:9
Prompt used
A ceramic coffee cup rests on a wooden table beside a sunlit window. Steam curls upward as the camera slowly pushes closer. A linen curtain moves gently in the background. Warm morning light, soft shadows. Audio: quiet room ambience and distant birdsong, no dialogue.
Creative example
A night market opening
Suggested prompt · street scene
- 15s
- 16:9
- 1080p
A food stall opens on a narrow evening street. Warm lanterns glow above a cook lifting the lid from a steaming pot. The camera slowly tracks past the counter. Audio: bubbling broth, a metal lid clink, and soft market chatter in the distance.
Creative example
A quiet coffee break
Suggested prompt · close-up scene
- 10s
- 9:16
- 1080p
A ceramic coffee cup rests on a wooden table beside a sunlit window. Steam curls upward as the camera slowly pushes closer. A linen curtain moves gently in the background. Warm morning light, soft shadows. Audio: quiet room ambience and distant birdsong, no dialogue.
Use Cases for Wan 3.0 Text to Video
Use a written scene to explore an idea before committing to a full production. Choose the action and framing for the place where the clip will be used.
Short social scenes
Plan a 9:16 opening for a short post: steam rising from breakfast, a door opening onto a garden, or a brief street scene. Keep the main action clear in the first few seconds.
Story and mood exploration
Try the same location with warm morning light or cool evening light to explore a story's atmosphere. Keep the action steady between attempts so you can compare mood without changing the entire scene.
Background clips for presentations
Describe a calm landscape or an uncluttered workspace for a wide presentation background. Leave visual space for titles you will add during editing, and review the soundtrack before combining it with narration.
Tips for Better Text-to-Video Results
Improve a Wan 3.0 Text to Video prompt by making the scene easier to follow. More instructions do not always mean a clearer result.
Keep the action achievable
Use one main action for a short clip. For a longer scene, describe a simple progression instead of a crowded list of events.
Make directions agree
Keep lighting, subject movement, and camera direction compatible. Replace conflicting style requests with a clear description of the look you want.
Compare one change at a time
Keep the settings steady when revising a prompt. Check the specific detail you changed so the next decision comes from the result.
Explore the Wan 3.0 generator for more creation workflows and output settings.
FAQ
What is Wan 3.0 Text to Video?
It creates a video from your description of a subject, setting, action, camera movement, and sound. Choose the output settings separately.
Can Wan 3.0 Text to Video make a 30-second clip?
Yes. Select 30s in the generator’s 2–30 second duration range. A duration written in the prompt does not change this setting.
Which aspect ratio should I choose?
Choose 16:9 for wide, 9:16 for vertical, or 1:1 for square. The generator also offers 4:3, 3:4, and adaptive framing.
Does Wan 3.0 Text to Video have a negative prompt field?
There is no separate negative prompt field. Write exclusions such as 'no dialogue' in the normal prompt; these are requests, not guaranteed restrictions.
How much does generation cost?
The credit estimate depends on model tier, resolution, and duration. Check it before generating. Purchased credits do not expire.
Will the video follow every timing instruction exactly?
Timing labels suggest pacing, without guaranteeing exact cuts. Review the output, simplify crowded sequences, and adjust your next attempt.
How do I write a prompt when I only have a rough idea?
Begin with one sentence naming the subject, action, and location. Add one lighting choice and one camera movement. For example, a boat crosses a calm bay at sunrise while the camera tracks sideways. Test that scene before introducing additional events.
Can I specify ambient sound without dialogue?
Yes. Describe the desired ambience and add 'no dialogue' to the scene description. Audio is included in the generation request. Listen to the returned clip because a written sound direction does not guarantee that every requested sound or exclusion will be followed.
Why does changing resolution change the credit estimate?
The selected model tier and resolution determine the credit rate per output second. Duration then changes the total. Compare the estimate with the same settings before generating; writing a different resolution inside the prompt does not change the controls or the estimate.
What should I change if my first result feels too busy?
Reduce the scene to one main action and remove competing camera directions. Keep the output settings unchanged so you can judge the revised prompt. In Wan 3.0 Text to Video, a simpler description makes it easier to identify which movement needs another adjustment.
Start with Wan 3.0 Text to Video
Write one scene, choose your settings, and create a first take.