Limited-Time 30% OFF!Get Offer
Wan 3.0 AI
0

Wan 3.0 text to video

Describe what happens, who speaks and how the camera moves. Wan 3.0 returns 2 to 30 seconds of video with sound in one pass.

A lighthouse beam sweeping rain over black rocks
Official sample
Prompt

A lighthouse beam sweeps through heavy rain over black rocks at night, waves detonating against the cliff.

Text to video examples

  • Coastal air — figure and glowing petalsOfficial sample
    Wan 3.0

    ENVIRONMENT: open coastal air — pale blue and violet sky with dry scumbled clouds, a thin band of teal sea at the lower edge, warm cream haze along the horizon. Backlight from behind the flower mass makes the petals glow near-white while her face and arms fall into warm shadow. STYLE: 24fps, gentle handheld drift, no camera shake spikes. Slow continuous push-in of about 8%, drifting a few degrees to the right so her face rotates marginally into the light. Shallow parallax between three planes: foreground drifting petals, mid-plane figure and bouquet, background sky and sea. Color tone: cool blue-lilac against cream-gold and umber. No morphing, no smoothing, no plastic skin, no added detail beyond the painting's own resolution.

  • A woman turns and smiles in a golden-hour fieldOfficial sample
    Kling 3.0

    Golden hour shot. A young woman with curly hair walking in a field of tall grass turns back to look at the camera and smiles genuinely. The low sun is behind her, creating a beautiful rim light (backlight) on her hair. Dust motes dancing in the light. Handheld camera feel, warm and nostalgic.

  • A kitten chasing a butterfly in a sunlit gardenOfficial sample
    MiniMax H3 Max

    A white kitten chases a butterfly across a sunlit garden. Gentle camera tracking, natural movement, soft afternoon light filtering through the leaves.

  • A fisherman rows across a misty lake at dawnOfficial sample
    Kling 4.0

    A fisherman in a yellow raincoat rows a small wooden boat across a calm misty lake at dawn, soft golden light breaking through the fog, gentle ripples, a heron lifts off in the background, slow cinematic dolly-in, natural ambient sound of water and distant birds

  • An astronaut finds a child with a glowing flower in city ruinsOfficial sample
    Wan 3.0

    A lone astronaut walks through the ruins of a once-busy city, surrounded by abandoned cars, overgrown skyscrapers, and trees growing through cracked streets. She discovers a small child standing inside an old convenience store, holding a glowing flower. The astronaut slowly removes her helmet as birds suddenly rise into the sky and sunlight breaks through the clouds. Emotional science-fiction film, grand post-apocalyptic environment, slow cinematic camera movement, wide establishing shots, intimate facial close-ups, realistic dust particles, warm sunlight contrasting with cold ruins, epic yet hopeful atmosphere.

  • Fireflies dancing in a twilight forestOfficial sample
    Kling 3.0

    Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement.

  • A warrior exploring sunlit monastery ruinsOfficial sample
    MiniMax H3 Max

    An aging warrior-monk in scorched ceremonial armor, a split ceramic mask and a humming prayer-band on his forearm + 0–4s: climbs silently along a cliffside terrace as insect-like surveyor drones comb the sun-bleached ruins, standing alone under as the camera rises over the ruined monastery. Sun-blasted post-apocalyptic sci-fi action, dust, heat haze, practical debris, sweeping crane tracking, silence broken only by wind.

  • A castle chef wins over a dragon with a fruit tartOfficial sample
    Kling 4.0

    A young royal chef stands inside a huge medieval castle kitchen, wearing a cream tunic and dark leather apron while dozens of elaborate dishes cover a long wooden table. A small dragon suddenly pushes its head through an open stone window. Everyone in the kitchen freezes. The chef cautiously offers it a roasted chicken. The dragon ignores it completely. He nervously raises a tiny fruit tart instead. The dragon’s eyes immediately brighten and it gently reaches toward the dessert. The camera begins behind hanging copper pans, tracks toward the chef, then pushes past him toward the dragon outside the window. Playful Western fantasy, detailed medieval kitchen, expressive creature behavior, cinematic comedy, realistic food and firelight.

  • Two piano tuners turn a mix-up into a duetOfficial sample
    Wan 3.0

    A young female piano tuner works alone inside an empty concert rehearsal hall, carefully adjusting the strings of a grand piano. A handsome young man enters from the opposite side carrying another tuning kit. They both stop when they realize they have been hired for the same piano. Without speaking, they sit on opposite sides and each plays a single note. She adjusts one string. He answers with another note. Their awkward disagreement slowly turns into an improvised musical conversation. The camera begins with a wide composition across the empty hall, glides toward the piano, then moves between their hands and subtle expressions. Romantic musical comedy, natural chemistry, elegant concert-hall acoustics, cinematic warm light.

  • A lone traveller crosses a dust storm in desert ruinsOfficial sample
    Kling 3.0

    Wide-angle shot. A lone figure with a large backpack walking through a dust storm-swept post-apocalyptic desert ruin. Wind blowing their cloak. Slow camera dolly out to reveal the desolate environment. Grainy film look.

  • A professor in a sunlit library asks a quiet questionOfficial sample
    MiniMax H3 Max

    Create a 5-second live-action Hollywood film shot in a bright university library. A thoughtful professor stands in a medium shot, turns slightly toward an unseen student, and calmly says, “What is the real?” Natural daylight, professional cinema camera, realistic performance, subtle camera drift, no close-up, no dark lighting, perfect lip sync.

  • A drone flies through mossy stone ruins at golden hourOfficial sample
    Kling 3.0

    Cinematic drone shot flying through ancient stone ruins covered in moss and vines at golden hour. Camera starts low, rises through crumbling archways, revealing a vast misty valley beyond. Volumetric light rays pierce through gaps in the stone. Epic scale, photorealistic, 8K quality.

What Wan 3.0 text to video makes from a prompt

A written scene becomes a video with sound

Wan 3.0 text to video turns a written description into a clip of 2 to 30 seconds. Describe the place, the people, what happens and how the camera moves, and the model builds the scene from your words alone.

Sound is made together with the picture: dialogue with matching lip movement, sound effects and background music. Put the lines a character says in quotes and name the sounds you want to hear.

The clip here is an official Wan 3.0 sample made from the prompt "A lighthouse beam sweeps through heavy rain over black rocks at night, waves detonating against the cliff."

A lighthouse beam sweeping through heavy rain over black rocks at night

Wan 3.0 text to video settings at a glance

Input
A text prompt
Room for a full shot list: who, where, what happens and how the camera moves.
Length
2 to 30 seconds
5 seconds is the default.
Quality
480P, 720P or 1080P
480P is the default. Move up once the scene looks right.
Frame shape
Adaptive, 16:9, 4:3, 1:1, 3:4 or 9:16
Pick 9:16 for phones or 16:9 for widescreen.
Sound
Always on
Dialogue, effects and music come with the picture.
Start from a picture
Image to video, Frames to video
Use them when you already have the opening or closing shot.

Wan 3.0 compared with other text to video AI models

Pick one in the Model menu at the top of the generator.

DefaultWan 3.0GenerateKling 4.0TryKling 3.0TryMiniMax H3 MaxTryMiniMax H3 Max TurboTry
Length2–30 s3–30 s3–15 s5–15 s5–15 s
Quality480P, 720P, 1080P720P, 1080P720P, 1080P, 4K480P, 768P, 1080P480P, 768P, 1080P
Pick it forScenes up to 30 s with dialogue and sound21:9 widescreen, up to 30 s4K, or a silent clip with sound turned offClips up to 15 s with synced audioThe lowest MiniMax price

What people make with Wan 3.0 text to video

  • Short story scenes

    Write the scene as a short shot list: how it opens, what happens, how it ends. Up to 30 seconds comes back in one take.

  • Product and brand spots

    Describe the product, the setting and one spoken line; the voice and music are generated with the picture.

  • A character who talks

    Give a character a few lines in quotes; the voice and the lip movement are generated together with the picture.

  • Mood clips for social

    Pick 9:16, describe the light, the weather and the sound, and use the clip as a background or a reel.

How to make a video from text with Wan 3.0

  1. 1
    Write the scene

    Write the scene

    Say where it is, who is in it, what happens in order and how the camera moves. Put spoken lines in quotes.

  2. 2
    Choose length and quality, then generate

    Choose length and quality, then generate

    Start at 480P and 5 seconds to check the scene, then raise the quality or length for the version you keep.

Plans and credits

First paymentUp to 20% OFF
07d 00:00:0007days00hrs00min00sec
  • Up to 500 images or 41 videos

    • All models, including Premium
  • Up to 1,250 images or 104 videos

    • All models, including Premium
  • Up to 3,750 images or 312 videos

    • Unlimited image generations

· No card required

Failed runs are refunded automatically · Cancel anytime

Wan 3.0 text to video FAQ