Veo 3.1 AI Video Generator

Video with sound in one render. Start from a prompt, a first and last frame, or up to 3 reference images.

Veo 3.1Pro
Generate

On Pro · A 4-second clip is 16 credits

Veo 3.1

Warm cinematic commercial, golden hour. A multigenerational family — grandparents, parents, young children — sits around a long wooden table in a backyard garden under glowing string lights, passing dishes of food, laughing and talking. [0-4s] Slow dolly along the table past smiling faces, shallow depth of field, warm backlight. [4-8s] Camera keeps gliding; grandmother laughs as a child leans in, glasses raised gently. Sound: natural ambient garden evening, soft cutlery clinks, overlapping friendly conversation and laughter. Realistic people with natural hands and faces. No on-screen text, no captions, no logos or lettering.

Veo 3.1

Warm cinematic commercial, golden hour. A multigenerational family — grandparents, parents, young children — sits around a long wooden table in a backyard garden under glowing string lights, passing dishes of food, laughing and talking. [0-4s] Slow dolly along the table past smiling faces, shallow depth of field, warm backlight. [4-8s] Camera keeps gliding; grandmother laughs as a child leans in, glasses raised gently. Sound: natural ambient garden evening, soft cutlery clinks, overlapping friendly conversation and laughter. Realistic people with natural hands and faces. No on-screen text, no captions, no logos or lettering.

Length
4, 6 or 8s
Resolution
720p or 1080p
Aspect ratio
16:9 or 9:16
Audio
Built in
Start from
Text, image or frames
Veo 3.1
Pro · 16 credits for 4s

Create with Veo 3.1

  1. Veo 3.1Pro
    Generate
    01

    Pick Veo 3.1

    Open Model Playground and choose Veo 3.1: write the scene and the lines, or start from an image or a first and last frame.

  2. Veo 3.1Pro
    Generate
    02

    Pick the length and resolution

    4, 6 or 8 seconds at 720p or 1080p, in 16:9 or 9:16. A 4-second clip is 16 credits at either resolution.

  3. 03

    Generate

    Veo 3.1 renders the clip with speech and sound in Model Playground, ready to download.

Veo 3.1Pro
Generate

See it in action

Whether you are making a product ad, a short film or a post for social, Veo 3.1 on Creatify gets you there faster.

For marketers: a table with the sea behind it

Friends on a seaside café terrace at sunset clink glasses and laugh, with the waves and the gulls in the same render.

For creators: a line spoken to camera

A handheld sunrise clip on a hotel balcony: she turns back and says “We almost didn’t book this place.” with gulls and waves behind her.

For filmmakers: set the first and last frame

Give Veo 3.1 a night shot and a sunrise shot of the same bottle, and it makes the 8 seconds between them: stars wheeling, sand blowing, the sun breaking behind the glass.

The prompts behind these clips

Every clip on this page came out of Veo 3.1 in Creatify with these exact prompts. The garden dinner and the seaside café are the 1080p generations. The perfume clip also started from a first and last frame. Copy one and make it yours.

  • Warm cinematic commercial, golden hour. A multigenerational family — grandparents, parents, young children — sits around a long wooden table in a backyard garden under glowing string lights, passing dishes of food, laughing and talking. [0-4s] Slow dolly along the table past smiling faces, shallow depth of field, warm backlight. [4-8s] Camera keeps gliding; grandmother laughs as a child leans in, glasses raised gently. Sound: natural ambient garden evening, soft cutlery clinks, overlapping friendly conversation and laughter. Realistic people with natural hands and faces. No on-screen text, no captions, no logos or lettering.

    Warm cinematic commercial, golden hour. A multigenerational family — grandparents, parents, young children — sits around a long wooden table in a backyard garden under glowing string lights, passing dishes of food, laughing and talking. [0-4s] Slow dolly along the table past smiling faces, shallow depth of field, warm backlight. [4-8s] Camera keeps gliding; grandmother laughs as a child leans in, glasses raised gently. Sound: natural ambient garden evening, soft cutlery clinks, overlapping friendly conversation and laughter. Realistic people with natural hands and faces. No on-screen text, no captions, no logos or lettering.

  • Cinematic lifestyle commercial, sunset. Friends at a seaside café terrace overlooking the ocean clink glasses and laugh together. [0-4s] Handheld camera drifts around the table, warm sun flare, sea behind them. [4-8s] They lean in laughing, one tells a story, others react; waves roll in below. Sound: waves and distant gulls, glasses clinking, relaxed overlapping chatter and laughter. No signs or storefronts in frame, no on-screen text, no captions, no logos or lettering.

    Cinematic lifestyle commercial, sunset. Friends at a seaside café terrace overlooking the ocean clink glasses and laugh together. [0-4s] Handheld camera drifts around the table, warm sun flare, sea behind them. [4-8s] They lean in laughing, one tells a story, others react; waves roll in below. Sound: waves and distant gulls, glasses clinking, relaxed overlapping chatter and laughter. No signs or storefronts in frame, no on-screen text, no captions, no logos or lettering.

  • Handheld travel video at sunrise. [0-4s] The camera follows a woman in a white hotel robe as she steps out barefoot through an open glass door onto a stone balcony overlooking a calm turquoise bay and a small fishing village. [4-8s] She leans on the railing, turns back to the camera with a sleepy smile and says: "We almost didn't book this place." Gulls and soft waves in the background. Authentic footage shot on a phone, natural daylight, real skin texture with pores, unretouched, slight handheld movement, realistic ambient sound, no music. Hands stay relaxed; nothing is opened, sprayed, poured or assembled. No logos, no brand names, no readable text anywhere. No on-screen text, no captions, no subtitles.

    Handheld travel video at sunrise. [0-4s] The camera follows a woman in a white hotel robe as she steps out barefoot through an open glass door onto a stone balcony overlooking a calm turquoise bay and a small fishing village. [4-8s] She leans on the railing, turns back to the camera with a sleepy smile and says: "We almost didn't book this place." Gulls and soft waves in the background. Authentic footage shot on a phone, natural daylight, real skin texture with pores, unretouched, slight handheld movement, realistic ambient sound, no music. Hands stay relaxed; nothing is opened, sprayed, poured or assembled. No logos, no brand names, no readable text anywhere. No on-screen text, no captions, no subtitles.

  • Luxury fragrance commercial, time-lapse cinematography; the bottle never moves and nothing touches it. [0-3s] Night over the desert: stars wheel slowly across the deep blue sky above the still glass bottle as the camera begins a slow push-in. [3-6s] Dawn spreads along the horizon, a soft wind lifts fine sand in glowing ribbons over the dune crests, shadows racing across the ripples. [6-8s] The sun breaks over the dunes behind the bottle and the amber liquid lights up like fire. A soft, low female voiceover says: "Wear the first light." Sound: desert wind, a fine hiss of sand, a slow warm string swell, a single bright chime as the sun appears. No people, no hands, no label, no logo, no on-screen text, no captions.

    Luxury fragrance commercial, time-lapse cinematography; the bottle never moves and nothing touches it. [0-3s] Night over the desert: stars wheel slowly across the deep blue sky above the still glass bottle as the camera begins a slow push-in. [3-6s] Dawn spreads along the horizon, a soft wind lifts fine sand in glowing ribbons over the dune crests, shadows racing across the ripples. [6-8s] The sun breaks over the dunes behind the bottle and the amber liquid lights up like fire. A soft, low female voiceover says: "Wear the first light." Sound: desert wind, a fine hiss of sand, a slow warm string swell, a single bright chime as the sun appears. No people, no hands, no label, no logo, no on-screen text, no captions.

What Veo 3.1 is good at

Dialogue in the same render

Put a line in quotes and someone says it, with the sound around it.

First and last frame

Upload the opening and closing image and Veo 3.1 makes the motion between them.

Up to 3 references

Images of a character, product or place keep them looking the same.

Extend by 7 seconds

Add 7 seconds to a clip you already made.

Sound at no extra cost

16 credits for 4 seconds, at 720p or 1080p.

G2

Rated 4.8/5 on G2

We’ve earned 40+ badges and 1000+ reviews on G2.

G2 Best Software 2025 — Top 50 Design ProductsG2 Summer 2025 — Best Results, Small BusinessG2 Summer 2025 — Best Usability, Small Business

Check out other models

Run the same prompt on another model in Model Playground and compare.

Veo 3.1 FAQ

Veo 3.1 is Google’s video generation model. In Creatify it makes 4, 6 or 8-second clips with sound from a text prompt, a starting image, a first and last frame, or up to 3 reference images, and it can extend a clip by 7 seconds.

Make your first Veo 3.1 clip

Write the scene, add a first and last frame or a few references, and get a clip with sound.