These are 40 complete, paste-ready prompts for Meta Muse Video — Meta Superintelligence Labs' text-to-video model, announced on July 7, 2026 alongside Muse Image and built on the same base. At preview it ranked #3 on the LMArena human-preference leaderboard for text-to-video, and its standout trait is native synchronized audio: picture and sound are generated in one pass, so you can describe dialogue, ambience and effects right in the brief. Every prompt below is written the way Muse rewards — one flowing paragraph with the subject, one action, one camera move, the sound world, and the aspect ratio stated in words.

Muse reasons about the brief and self-revises before it finalizes, so detailed, ordered prose lands closer. There is no Settings: line, no --flags, and no resolution, frame rate or seconds — Meta hasn't published those numbers, so describe length in words instead. For the pattern behind these, read how to prompt Meta Muse Video for realistic video and keep the Muse Video prompt cheat sheet open. Coming from the image side? Compare with the best Meta Muse Image prompts.

Advertisement

Cinematic b-roll

Establishers live and die on the camera move. Name one move per shot, set the light, keep the scene simple, and let the described sound world carry the mood.

1. Foggy Valley Dawn Aerial

A wide mountain valley at dawn, layered pine ridges fading into low drifting fog, thin clouds sliding between the peaks. The camera makes a slow aerial push forward over the treetops as the first golden light breaks on the horizon, cinematic and calm, epic in scale. Soft wind moves through the trees with distant birdsong and no music. Widescreen 16:9, one smooth continuous shot.

Why it works: one slow aerial move plus drifting fog gives Muse a single clear direction of motion, so the shot feels directed rather than jittery.

2. Rain-Slicked Neon Alley

A narrow rainy alley in a neon-lit Asian city at night, red and blue signs reflected in the wet pavement, steam curling up from a vent. The camera glides in a slow dolly forward down the center of the lane, shallow depth of field, moody cinematic light. Rain patters on the tin awnings, a distant train hums, and no dialogue. Vertical 9:16, a single unbroken take.

Best for: title backgrounds and moody vertical intros — the named rain and awning sounds trigger Muse's synced ambience.

3. Coastal Cliff Reveal

A rugged coastline with turquoise waves crashing against tall cliffs and a lone white lighthouse on the headland. The camera rises and pulls back as an aerial shot to reveal the full coast under bright midday sun, deep blue ocean, crisp natural color, smooth cinematic motion. Waves boom against the rocks below and gulls cry overhead. Widescreen 16:9, one continuous shot.

Why it works: a rise-and-pull-back is the strongest reveal move, and one landmark anchors the eye as the frame widens.

4. Desert Dunes at Golden Hour

Vast rolling sand dunes at golden hour, sharp wind-carved ridgelines casting long shadows, fine sand streaming off the crests in the breeze. The camera tracks slowly sideways along a ridge, warm amber light, minimal and meditative, cinematic color grade. A low steady wind hisses over the sand with no other sound. Widescreen 16:9, a single smooth take.

Best for: calm establishers and title cards — one sideways track keeps the motion clean while the streaming sand adds life.

5. City Rooftop Dusk

A modern city skyline at dusk turning to night, office windows lighting up in sequence, faint headlight streaks on the streets far below. The camera holds a static lock-off with a very slow push-in toward the tallest tower, deep blue-to-orange sky, polished and cinematic. A soft city hum drifts up with a distant siren far away. Widescreen 16:9, one continuous shot.

Why it works: a nearly locked camera lets the changing lights be the motion, which keeps a wide cityscape from smearing.

6. Forest Stream Close-Up

A close-up of clear water tumbling over mossy rocks in a sunlit forest stream, tiny bubbles swirling in an eddy, a single leaf spinning past. The camera makes a gentle slow push-in along the water, soft dappled light through the canopy, peaceful and fresh, shallow focus. The stream gurgles and burbles with soft birdsong above. Portrait 4:5, a single unbroken take.

Best for: nature loops and calm backdrops — the burbling water is exactly the kind of source-linked sound native audio nails.

People & motion

Describe the person, give them one action, and let the camera carry it. Muse holds a single figure in motion — and their expression — far better than a crowd.

7. Barista Pouring Latte Art

A barista in an apron pours steamed milk into a cup to form a leaf of latte art, steam curling upward from the cup. The camera makes a slow push-in on her hands and the cup, soft window light with a warm bounce, shallow focus, cozy documentary feel. The milk trickles softly, the machine hisses in the background, and quiet cafe chatter fills the room. Widescreen 16:9, one continuous shot.

Why it works: the pour and steam are small contained motions, so a slow push-in keeps them sharp while the ambient cafe sound sets the scene.

8. Runner at Sunrise

A young woman jogs along an empty seaside promenade at sunrise, breath visible in the cool air, ponytail bouncing with each stride. The camera tracks beside her at a steady matching pace, warm low backlight rimming her silhouette, subtle lens flare, motivational sports feel. Her steady footfalls tap the pavement, waves break softly off to the side, and the breeze rushes past. Widescreen 16:9, a single continuous shot.

Best for: fitness and lifestyle ads — the tracked footfalls and waves give the run a real, grounded rhythm.

9. Potter at the Wheel

A ceramicist's wet hands shape a spinning clay bowl on a pottery wheel, the clay rising and narrowing under her fingers, water glistening on the surface. The camera makes a slow orbit around the wheel from the side to the front, warm natural window light, calm focused craft mood, fine detail on the clay. The wheel whirs steadily and the wet clay squelches under her palms. Widescreen 16:9, one smooth take.

Why it works: a slow orbit adds depth while the contained hand motion stays stable, and the whir plus squelch reads as tactile.

10. Dancer in an Empty Studio

A contemporary dancer in flowing fabric moves through a slow expressive turn in a bright empty studio, dust motes floating in a shaft of light. The camera sweeps in a gentle arc around her, soft directional daylight, elegant and emotional, gentle motion blur on the fabric. Her bare feet brush and pivot on the wooden floor with soft breath, and a single sustained piano note holds underneath. Widescreen 16:9, one continuous shot.

Best for: expressive brand and music moments — one turn plus one arc keeps the choreography clean and readable.

11. Child Blowing a Dandelion

A laughing child in a summer meadow blows the seeds off a dandelion, the seeds drifting and scattering into the warm air. The camera eases in as a handheld tracking shot toward their face, bright golden afternoon light, joyful and candid, shallow focus. The child giggles, a soft breeze rustles the grass, and crickets chirp faintly in the distance. Vertical 9:16, a single unbroken take.

Why it works: the drifting seeds give lively secondary motion while the child's face stays the calm anchor, and the giggle lands as native audio.

12. Chef Plating a Dish

A chef's hands carefully plate a fine-dining dish, a spoon dragging a streak of sauce across a white plate and placing a delicate herb on top. The camera makes a slow overhead push-down onto the plate, crisp directional restaurant-pass light, precise and premium, shallow focus. The sauce spoon clinks softly on the porcelain and a busy kitchen simmers and clatters behind. Square 1:1, one continuous shot.

Best for: food and restaurant social clips — the overhead move plus the clink of the spoon feels editorial and appetizing.

Advertisement

Talking & dialogue — native audio

This is Muse Video's headline edge: dialogue, ambience and effects are generated with the picture in one pass. Put spoken lines in quotes, keep them short, and name the visible object that makes each sound. Sync is still improving, so favor one calm line to camera per shot rather than a fast exchange.

13. Barista Line to Camera

A friendly barista behind a coffee counter looks into the lens and says warmly, "Your usual? Coming right up." The camera holds a gentle push-in on her face and shoulders, soft morning window light, cozy and inviting. The espresso machine hisses and steams as she speaks, cups clink on the saucer, and low cafe chatter fills the background. Vertical 9:16, a single continuous shot.

Why it works: one short line to camera plus a named machine hiss keeps the audio believable without demanding perfect lip-sync.

14. Podcast Host Welcome

A podcast host in headphones leans toward a large studio microphone and says calmly, "Welcome back to the show." The camera holds a slow push-in from a slight low angle, warm key light with a soft blue rim, moody studio mood. His voice is close and clear through the mic, a faint room tone hums, and a chair creaks softly as he settles in. Widescreen 16:9, one continuous shot.

Best for: channel intros — naming the microphone as the sound source cues the intimate, close-mic voice.

15. Street Vendor Call

A cheerful street-food vendor at a sizzling grill looks up and calls out, "Fresh and hot, come try one!" The camera tracks slowly past the stall, warm string-light glow, lively night-market mood, shallow focus on his face. The grill sizzles and pops as he flips skewers, a crowd murmurs around the stall, and a distant scooter buzzes past. Vertical 9:16, a single unbroken take.

Why it works: the sizzling grill is a clearly visible sound source, so the effect locks to what's on screen while the call adds energy.

16. Founder Product Reveal

A startup founder in a clean minimalist office holds up a small gadget to the camera and says confidently, "This is what we've been building." The camera makes a slow push-in from her hands up to her face, bright soft daylight, crisp modern tech look. Her voice is clear and close, the device clicks softly as she turns it, and a quiet office hum sits underneath. Widescreen 16:9, one continuous shot.

Best for: launch teasers — the device click naming the object keeps the reveal grounded and tactile.

17. Grandmother in the Kitchen

A warm elderly grandmother stirs a pot at the stove, turns her head toward the camera and says softly, "Almost ready, sit down." The camera holds a gentle static frame with a faint push-in, warm cozy kitchen light, nostalgic and homely. The spoon scrapes and taps the pot, the stew bubbles gently, and a kettle whistles faintly in the background. Portrait 4:5, a single continuous shot.

Why it works: a slow single line plus the bubbling pot and spoon taps stacks several source-linked sounds into one homely scene.

18. Kid Reads a Bedtime Line

A small child in pajamas holds an open storybook by a bedside lamp, looks up and reads out loud, "And they lived happily ever after." The camera makes a soft slow push-in on the book and the child's face, warm low lamplight, tender and quiet. The child's voice is gentle, a page rustles as they turn it, and soft rain taps the window behind them. Vertical 9:16, one continuous shot.

Best for: heartfelt family and storytime content — the page rustle and window rain give the calm line a real room around it.

Product & ads

Center the product, keep the background clean, and choose one controlled camera move — a slow rotation or a macro push reads as premium. Name the one sound the product makes so the audio stays tied to the object.

19. Perfume Bottle Turn

A faceted glass perfume bottle with a gold cap stands on a wet black reflective surface, a soft swirl of pink mist drifting behind it. The camera makes a slow single-axis rotation around the bottle, elegant studio lighting with a bright rim highlight on the edges, luxury commercial look, crisp reflections. A soft airy shimmer tone rises and the atomizer gives one gentle spritz. Square 1:1, one smooth continuous shot.

Why it works: a slow single-axis turn on a clean set is the classic product-hero move, and the single spritz ties the audio to the object.

20. Sneaker Splash

A white-and-orange running sneaker steps into a shallow puddle in slow motion, water bursting up in a crown of droplets around the sole. The camera tracks at ground level as a punchy macro shot, hard directional light, high-contrast commercial color, dark studio background, crisp frozen droplets. A deep whoosh and a sharp water splash hit as the shoe lands. Widescreen 16:9, a single continuous shot.

Best for: energetic footwear ads — the ground-level track plus the splash sound sells the impact.

21. Watch Floating Spin

A luxury chronograph watch floats and slowly rotates above an open minimalist box, soft particles of light drifting around it. The camera holds steady with a subtle push-in, clean charcoal-to-deep-blue gradient background, crisp rim lighting on the case and bracelet, modern premium tech-commercial feel. The watch ticks crisply and a soft rising synth tone swells underneath. Widescreen 16:9, one smooth take.

Why it works: a floating slow spin on a gradient set is a reliable luxury look, and the crisp tick is the one sound the object should own.

22. Cola Ice Pour

Dark cola pours over ice cubes into a frosted glass, bubbles fizzing and rising, condensation beading on the outside. The camera holds a static lock-off with a subtle slow push-in, bright appetizing side light, rich caramel tones, refreshing high-contrast commercial look. The cola glugs as it pours, the ice cracks and clinks, and the drink fizzes brightly. Vertical 9:16, a single continuous shot.

Best for: beverage ads — a nearly locked camera lets the pour be the only motion while the fizz and clink carry the sound.

23. Serum Droplet Macro

A frosted-glass dropper releases a single glossy golden droplet onto a smooth cream surface, the drop landing and rippling outward in slow motion. The camera holds a tight macro with a barely-there push-in, soft even beauty lighting, minimalist studio in sage and cream tones, calm premium mood. A soft delicate plip marks the drop and a gentle ambient pad hums underneath. Square 1:1, one continuous shot.

Why it works: a locked macro keeps the drip controlled, and the tiny plip is exactly the kind of precise source sound native audio handles.

24. Headphones on a Plinth

A pair of matte-black over-ear headphones rests on a raw concrete plinth, a slow ring of light sweeping around the cups. The camera makes a slow three-quarter orbit around the plinth, dramatic single hard key light with a crisp grounding shadow, cool grey studio, bold premium look. A deep bass note thumps once and a clean high chime rings as the light passes. Widescreen 16:9, one smooth take.

Best for: audio and tech brands — the bass thump and chime literally advertise what the product is for.

Advertisement

Anime & stylized

Name the exact style plus line weight and shading, keep one character in frame, and add a camera move for energy. Muse can also hold a short multi-shot script in one prompt.

25. Anime Rooftop Sunset

A young anime girl with short teal hair stands on a school rooftop at sunset, her hair and skirt swaying in the wind, then she turns her head toward the camera and smiles softly. The camera makes a slow push-in on her face, warm orange light and long shadows, wistful Makoto Shinkai-inspired style, crisp clean line art, detailed sky. A gentle breeze whistles and a soft nostalgic piano melody plays. Widescreen 16:9, one continuous shot.

Why it works: the swaying hair supplies motion while her face stays calm — exactly what anime frames handle beautifully.

26. Ghibli Meadow Walk

A girl in a red dress walks through a rolling green meadow of wildflowers under a huge blue sky with fluffy clouds, grass and hair swaying in the breeze. The camera tracks slowly beside her, soft hand-painted Studio Ghibli-inspired style, warm nostalgic light, gentle and dreamy. A light breeze rustles the grass, birds chirp overhead, and a warm orchestral theme swells softly. Widescreen 16:9, a single continuous shot.

Best for: painterly openers — a side track plus swaying grass gives that wandering feel without complex character animation.

27. Cyberpunk Courier Ride

A cyberpunk courier on a glowing hover-bike weaves between neon skyscrapers at night, trails of light streaking past. The camera swoops alongside the bike as a dynamic tracking shot, rain streaking through the headlights, vibrant cel-shaded anime style with bold outlines, high energy, motion blur. The hover-bike whines and roars, rain hisses against it, and a driving synth track pulses. Widescreen 16:9, one continuous shot.

Why it works: a clear alongside track keeps the chase fast and directed, and the whine plus synth pushes the energy.

28. Cel-Shaded Sword Draw

A lone samurai in a bamboo forest slowly draws a katana, petals and mist drifting past, the blade catching a glint of light. The camera makes a dramatic low-angle push-in on the draw, bold cel-shaded anime style with thick outlines and flat shading, tense and quiet, sharp rim light. The steel rings as it clears the scabbard, wind rushes through the bamboo, and the silence holds. Widescreen 16:9, a single continuous shot.

Best for: action anime beats — the slow draw plus one push-in builds tension, and the ringing steel is the payoff sound.

29. Watercolor Cat by a Window

A fluffy grey cat curls on a windowsill in the rain, its tail flicking slowly and ears twitching. The camera makes a slow gentle push-in, soft loose watercolor illustration style with visible paper texture, muted blue and warm-cream palette, calm and cozy, blurred rain beyond the glass. Soft rain patters against the window and the cat purrs quietly. Square 1:1, one continuous shot.

Why it works: naming the medium and a slow push-in keeps the painterly texture intact, while the purr and rain add warmth.

30. Anime Three-Shot Sequence

An anime short in warm sunset color with clean line art. Shot 1: a boy stands on a train platform holding a letter, wind lifting his hair. Shot 2: a close-up of his determined face as he looks up. Shot 3: he runs toward the departing train, cherry petals swirling behind him. Smooth cuts between shots, cinematic and emotional. The train rumbles and its horn sounds, wind gusts, and a rising orchestral theme carries across the cuts. Widescreen 16:9, a short continuous sequence.

Why it works: Muse holds the same character across a Shot 1 / Shot 2 / Shot 3 script, so you get a tiny storyboard with sound that carries through the cuts.

Action & VFX

Give the effect a clear cause and one camera move, and let the audio hit on the beat. One dramatic moment per shot reads better than a stack of them.

31. Superhero Rooftop Landing

A caped superhero lands hard on a rain-slicked rooftop at night, cracking the concrete with a shockwave of dust and water, cape settling behind them. The camera holds a low hero angle looking up and pushes in slowly, dramatic blue moonlight with a warm city glow behind, cinematic blockbuster look. A heavy impact boom hits, debris skitters, and a low brass sting swells. Widescreen 16:9, one continuous shot.

Why it works: the impact gives a burst of motion up front, then the slow push-in lets it settle — and the boom lands on the landing.

32. Dragon Over a Valley

An enormous scaled dragon sweeps low over a misty green valley at dawn, wings beating, trees bending in the downdraft. The camera flies alongside the dragon as a sweeping aerial tracking shot, mountains and a river beyond, epic fantasy color grade, cinematic scale. Each wingbeat thumps with a deep wind rumble, the dragon lets out a low roar, and an epic score swells. Widescreen 16:9, a single continuous shot.

Best for: fantasy trailers — a fly-alongside track keeps the creature centered, and the wingbeat thumps sell its weight.

33. Explosion Walk-Away

A rugged action hero in a leather jacket walks calmly toward the camera as a massive fireball erupts behind him, debris and sparks flying; he does not look back. The camera dollies back in slow motion keeping pace with him, warm orange firelight on his face, gritty blockbuster grade. The explosion roars and crackles behind him while his boots crunch steadily on gravel. Widescreen 16:9, one continuous shot.

Why it works: the don't-look-back setup gives two clear layers — steady subject, chaotic background — and the dolly-back holds the frame while the roar fills the rear.

34. Motorcycle Tunnel Ride

A sport motorcycle speeds through a neon-lit tunnel at night, light strips streaking past on the walls, the rider leaning into the motion. The camera chases just behind the bike as a dynamic tracking shot, reflections racing across the wet asphalt, high-energy cinematic grade, motion blur. The engine snarls and echoes off the tunnel walls and a fast electronic beat drives underneath. Widescreen 16:9, a single continuous shot.

Best for: high-adrenaline openers — the chase-behind track plus the echoing engine sells the speed.

35. Underwater Whale Pass

An enormous humpback whale glides slowly through deep blue ocean water, shafts of sunlight streaming down from the surface, tiny fish scattering as it passes. The camera drifts alongside the whale as a slow tracking shot, serene underwater light with floating particles, majestic and calm, cinematic. Muffled whale song calls out low and long and gentle water pressure hums around it. Widescreen 16:9, one smooth continuous shot.

Why it works: the drifting-alongside track keeps the whale grand and unhurried, and the low whale song is a haunting native-audio moment.

Advertisement

Image-to-video

These animate a still you upload in image-to-video mode. Describe only the motion and audio you want added, and lock identity — keep the face, wardrobe and background identical — so Muse moves the frame without redrawing it. See the full image-to-video pack for more.

36. Portrait Comes to Life

Animate this portrait: the person blinks naturally and gives a soft warm smile, hair moving slightly in a gentle breeze, with a subtle head turn toward the camera. Keep the face, wardrobe and background identical to the photo, add only a slow subtle push-in, natural and realistic. A quiet room tone and a soft breath are the only sounds. Portrait 4:5, a single continuous shot.

Why it works: naming small natural motions and locking identity gives a believable live portrait without distorting the face.

37. Landscape Photo Parallax

Animate this landscape photo with gentle parallax: clouds drift slowly across the sky, the water ripples and reflects, and grass and leaves sway in a light breeze. Keep every element, color and the composition identical to the image, add only a slow cinematic push-in for depth, calm and alive. A soft wind and distant birdsong fill the air. Widescreen 16:9, one continuous shot.

Best for: turning a photo into a living wallpaper — assigning motion to layers (sky, water, foliage) creates convincing depth while the frame stays locked.

38. Old Family Photo Animated

Gently animate this vintage family photograph: the people breathe and blink softly with small natural head movements and warm smiles, faint film grain and a subtle slow zoom. Keep the face, wardrobe and background identical to the original — do not change anyone's features. A faint warm room tone and a soft nostalgic music-box melody play underneath. Classic 4:3, a single continuous shot.

Best for: memory and heritage content — locking identity keeps likenesses true while the gentle motion brings it to life.

39. Product Still to Spin

Animate this product still: the bottle rotates slowly on the spot while a soft light sweep passes across its surface and a few particles of light drift by. Keep the label, shape, colors and background identical to the image, add only the slow rotation, clean premium commercial feel. A soft airy shimmer tone rises gently. Square 1:1, one smooth continuous shot.

Why it works: a single slow rotation is the safest motion to add to a locked product frame, so the label stays crisp and correct.

40. Pet Portrait Speaks

Animate this photo of a dog: it tilts its head, blinks, and gives a single happy bark toward the camera, ears perking up. Keep the face, fur, wardrobe and background identical to the photo, add only a slow subtle push-in, playful and warm. The bark rings out clearly and a soft home room tone sits underneath. Vertical 9:16, a single continuous shot.

Best for: playful pet and social clips — the single bark tied to the visible action is a clean, believable native-audio moment.

Once a shot lands close, keep the Muse Video prompt cheat sheet open for the camera-move and audio phrasing, read how to prompt for realistic video for the formula behind the b-roll, and browse the native-audio prompt collection for more dialogue and sound-driven scenes.

Frequently Asked Questions

What is Meta Muse Video and who makes it?

Meta Muse Video is a text-to-video model from Meta Superintelligence Labs, announced on July 7, 2026 alongside Muse Image and built on the same pretraining base. At preview it ranked #3 on the LMArena human-preference leaderboard for text-to-video. It generates picture and synchronized audio in one pass, and it is rolling out to creators through the Meta AI app, meta.ai, Instagram Reels and Stories, and WhatsApp.

How do I write a good Meta Muse Video prompt?

Write one flowing natural-language paragraph, not comma-tags and not --flags. Name the subject and its look, give it one clear action, state one explicit camera move such as a slow push-in, pull-back, dolly, orbit, aerial or static lock-off, then the setting, lighting and mood, then the sound world, and finish by stating the aspect ratio in words. Because Muse reasons about the brief and self-revises before finalizing, longer, well-ordered prose lands closer. Do not put resolution, frame rate or seconds in the prompt — Meta has not published those numbers.

How does Meta Muse Video's native audio work?

Sound is generated in the same pass as the picture — dialogue, ambience, sound effects and music together. In the prompt, describe the sound world and name which visible object makes each sound, for example the fizz from the glass, the rain on the awning, or the line a character speaks. Keep spoken lines short and put them in quotation marks. Meta notes audio-video sync is still improving, so do not rely on frame-perfect lip-sync.

Does Muse Video do dialogue and lip-sync?

Yes, it can generate spoken dialogue as part of the native audio pass, and you cue it by putting the words in quotes and naming who says them. Because sync is still improving, keep each line to a short sentence, favor a single speaker per shot, and treat lip-sync as approximate rather than exact. For talking-head clips, one calm line delivered to camera works far more reliably than a fast back-and-forth.

What is the difference between text-to-video, image-to-video and video-to-video?

Text-to-video builds the whole clip from a written description. Image-to-video animates a still you provide — you describe only the motion and audio to add and lock identity so the face, wardrobe and background stay the same. Video-to-video restyles or extends an existing clip. Use text-to-video to invent a scene, image-to-video when you already have the exact frame, and video-to-video to change the look of footage you already have.

What aspect ratios does Meta Muse Video support?

State the ratio in plain words at the end of your prompt rather than with a flag. Common options are square 1:1, landscape 16:9, vertical 9:16, portrait 4:5 and classic 4:3. Every prompt on this page ends with its ratio spelled out, so pick vertical 9:16 for Reels and Stories, widescreen 16:9 for YouTube, and square 1:1 for feed posts.

Where can I use Meta Muse Video?

It is rolling out to creators inside the Meta AI app, at meta.ai, in Instagram Reels and Stories, and in WhatsApp. Because it shares a base with Muse Image, the two feel consistent to prompt — you brief them the same way, in prose, with the aspect ratio in words. Paste any prompt on this page into the Meta AI app to try it.

How is Muse Video different from Muse Image?

They share the same pretraining base and the same prose-first prompting style, so the writing habits carry over. Muse Video adds time and sound: you specify one motion and one camera move per shot, and you describe a sound world with dialogue, ambience and effects because audio is generated natively alongside the picture. Muse Image is a still; Muse Video is its motion-and-audio sibling.

Advertisement