Skip to content

Veo 3 and Veo 3.1 Video with its own sound

Google's video model turns a scene and the lines people say into 4, 6 or 8 seconds with speech, effects and ambience, up to 4K.

Make a Veo 3.1 videoPlans from $19 a month

Seedance 2.5 · 20 s · 480p

Grok Imagine 1.5 · 6 s · 480p

Veo 3 or Veo 3.1?You get 3.1, the current one.

Veo is Google's video model. Veo 3.1 is the newer version of Veo 3, and the one Sceneform runs, as Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite.

Length
4, 6 or 8 s
Shape
16:9 or 9:16
Resolution
Up to 4K
Sound
On by default
Takes per run
Up to 4
Extend
+7 s

Prompting Veo for sound?Write it like a scene.

Veo 3.1 makes the sound with the picture. Name who speaks, put the line in quotes, and list what you want to hear.

Late-night subway car, almost empty, harsh fluorescent light, city lights streaking past the windows.

Two friends in their twenties in streetwear slump on the bench, her head on his shoulder.

0-4 s: the train pulls out of a station, she sits up, looks back at the platform

She

'We missed our stop. Again.'

4-8 s: he shrugs, grins

He

'Worth it.'

She bursts out laughing.

Sound: the train rattling over the tracks, the door chime.

The prompt, as one paragraph
Two friends on a late-night subway realize they missed their stop, and she bursts out laughing, made with Grok Imagine 1.5

Grok Imagine 1.5 · 8 s · 480p

Scene and action
What you see
Who speaks, then the line in quotes
Who speaks, and what they say
Sound
Effects and ambience
Seconds, like 0-4 s
When each beat happens

More than a prompt.Three ways to steer a shot.

  1. 1

    Start from a photo

    Upload a photo and the clip starts on it. Write what happens next and what they say.

    • A phone selfie of a young woman with short pink hair and a black puffer jacket on a city street at night, snow starting to fall

      Start frame

    A woman with pink hair films a selfie on a city street at night as the first snow falls, looks up and laughs, made with Seedance 2.5

    Seedance 2.5 · 5 s · 480p

    Seedance 2.5 · Handheld phone selfie. Tiny snowflakes drift down and melt in her pink hair. She looks up at the sky, then back into the lens, laughs and says in English, excitedly, {First snow of the year!} Street noise behind her. No subtitles.

  2. 2

    Give it the first and last frame

    Add a second image and the clip ends on it. Veo 3.1 fills the seconds in between.

    • A dancer in a white suit standing still in an empty white studio

      Start frame

    • The same dancer with one arm raised, her suit and the studio splashed with pink, yellow and blue paint

      Last frame

    Paint bursts around a dancer in a white suit in a white studio until she and the walls are covered in color, made with Kling 3.0

    Kling 3.0 · 8 s · 720p

    Kling 3.0 · Paint bombs burst around the dancer from every side. She spins and leaps as hot pink, yellow and blue paint splashes across her white suit and the white walls, then she lands and raises one arm. Slow motion. Sound: wet paint bursts and a deep bass hit.

  3. 3

    Hand it three references

    A person, a product and a place go into one shot. References work on Veo 3.1 and Fast, at 8 seconds.

    • A phone photo of a woman with locs in a white T-shirt and jeans against a cream wall

      Person

    • A long red patent vinyl trench coat with a belt, laid flat

      Product

    • An empty car wash tunnel at night with pink and blue brushes and foam on the wet floor

      Place

    The woman from the photo in the red vinyl trench coat walks through a car wash lit pink and blue, turns to the camera, then walks out into the night, made with Wan 2.7

    Wan 2.7 · 10 s · 720p

    Wan 2.7 · Image 1 wears the red vinyl trench coat from Image 2 and walks through the car wash from Image 3 at night. Shot 1 [0-4s] Wide shot from the tunnel entrance: she walks toward the camera between the spinning pink and blue brushes, foam falling around her. Shot 2 [4-7s] Hard cut, close-up: she turns her head to the lens as water spray beads on the glossy red coat. Shot 3 [7-10s] Low angle from behind: she walks out of the tunnel into the rain, the coat swinging. Sound: brushes whirring, water hissing, a slow heavy bass beat.

Veo 3.1, Fast or Lite?Draft on Lite. Finish on 3.1.

Lite makes up to four takes of a prompt at a time, with sound. When one works, run the same prompt on Veo 3.1.

“A highliner in a bright orange jacket and a white helmet walks a thin line strung between two tall granite spires, high above a sea of clouds at sunrise, a leash clipped from her harness to the line. Halfway across, a gust hits: the line sways, she drops into a low crouch with both arms out wide, holds, then rises and walks on. The spires drop away sheer into the clouds far below, and the low sun turns the cloud tops gold. Realistic adventure film, one low sun against a cold blue sky. Wide shot from a ledge level with the line, framing her whole body, the far spire and the drop below; the camera slowly pushes in and ends on her standing tall in the middle of the line. Sound: <wind gusting past the rock>, <the line creaking>, <a carabiner clinking>. Her mouth stays closed, no narration, no music.”

  • The 9:16 take: the highliner crouches on the line between two granite spires above the clouds, made with Seedance 2.5Take 1
  • The 1:1 take: the highliner holds her arms out on the line, high above the clouds, made with Seedance 2.5Take 2
  • The 16:9 take: the highliner crouches with her arms out as the line sways, made with Seedance 2.5Take 3
  • The 21:9 take: the highliner walks the line far above a sea of clouds at sunrise, made with Seedance 2.5Take 4
Takes of one prompt on Seedance 2.5, in 9:16, 1:1, 16:9 and 21:9, 480p
A highliner in an orange jacket crouches as a gust sways her line between two granite spires above the clouds, then walks on, made with Seedance 2.5

Seedance 2.5 · 8 s · 480p

Take 3 on Seedance 2.5, 16:9, 480p

Veo 3.1 Lite

Drafts with sound, at the lowest cost.

Resolution
720p or 1080p
Frames
Start and last frame
References
None
Extend
No

Veo 3.1 Fast

Veo's look and sound for less.

Resolution
720p, 1080p or 4K
Frames
Start and last frame
References
Up to 3
Extend
+7 s

Veo 3.1

Dialogue, realism and 4K for the final cut.

Resolution
720p, 1080p or 4K
Frames
Start and last frame
References
Up to 3
Extend
+7 s

All three make 4, 6 or 8 seconds in 16:9 or 9:16, with sound you can switch off.

Start a Lite draft

Need more than 8 seconds?Extend the shot by 7.

Extend picks up where your clip ends and adds 7 seconds with sound, at 720p. It works on Veo 3.1 and Fast.

  1. A mountain biker races down a forest trail and launches off a jump over a ravine, made with Seedance 2.5

    Seedance 2.5 · 10 s · 480p

    Your clip, on Seedance 2.5 · 0 to 10 s

    One continuous shot. Downhill mountain bike race through a steep pine forest in late afternoon light. A rider in a red full-face helmet and black jersey. The camera chases her at ground level, inches behind the rear wheel, dust and pine needles blasting into the lens. 0-4s: she tears down a root-covered chute, the bike bucking, branches whipping past. 4-8s: the trail drops into a rock garden and the camera swings wide and low to her side at full speed. 8-10s: the trees open onto a giant dirt jump over a ravine; she hits the lip and launches, and the shot ends with her mid-air above the drop, sky behind her. <tires ripping through dirt, chain slapping, hard breathing, wind roar cutting to silence at takeoff>

  2. The rider lands, races into a finish area full of red smoke and a cheering crowd, and shouts, made with Seedance 2.5 Extend

    Seedance 2.5 Extend · +10 s · 480p

    Extend, on Seedance 2.5 Extend · 10 to 20 s

    Continue the 10 seconds after @Video1. She is still mid-air above the ravine. 0-2s: the camera rises with her as she whips the bike sideways at the top of the jump. 2-5s: she slams down on the landing in an explosion of dust and the camera dives after her, chasing low. 5-8s: she rails a huge berm, spraying dirt across the lens, and bursts out of the trees into a finish area lined with a roaring crowd and red smoke flares. 8-10s: she skids sideways across the finish line, rips off her goggles and shouts {LET'S GO!} <landing impact, dirt spray, crowd erupting, air horns>

How to use Veo 3Four steps on Sceneform.

  1. 1

    Pick a Veo

    Open Video and choose Veo 3.1, Veo 3.1 Fast or Veo 3.1 Lite.

  2. 2

    Write the scene

    Who is there, what happens, the lines in quotes, the sounds and the camera.

  3. 3

    Add images if you have them

    A start frame, a last frame, or up to three references.

  4. 4

    Set the shot and generate

    16:9 or 9:16, 4 to 8 seconds, 720p to 4K. Up to four takes at once.

Try Veo 3.1

Simple pricing that scales with you.

Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.

Creator

$19/month

Billed monthly

For solo creators posting every week

500 credits every month

  • Up to 250 AI images
  • Up to 25 Veo 3.1 Fast clips
  • Up to 1.5 hours of AI voiceover
  • Roll over up to 1,000 credits
Start with Creator

Pro

Most popular
$49/month

Billed monthly

For creators posting daily across channels

1,300 credits every month

  • Up to 650 AI images
  • Up to 65 Veo 3.1 Fast clips
  • Up to 4 hours of AI voiceover
  • Roll over up to 2,600 credits
Start with Pro

Studio

$99/month

Billed monthly

For brands and production teams

2,700 credits every month

  • Up to 1,350 AI images
  • Up to 135 Veo 3.1 Fast clips
  • Up to 9 hours of AI voiceover
  • Roll over up to 5,400 credits
Start with Studio

Scale

$199/month

Billed monthly

For agencies running always-on content

5,500 credits every month

  • Up to 2,750 AI images
  • Up to 275 Veo 3.1 Fast clips
  • Up to 18 hours of AI voiceover
  • Roll over up to 11,000 credits
Start with Scale
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights

Want checkout, comparison tables, or a custom volume? See the full pricing page

Veo 3 FAQ

The rider lands, races into a finish area full of red smoke and a cheering crowd, and shouts, made with Seedance 2.5 Extend

Your scene, with sound.Make it with Veo 3.1.

Try Veo 3.1

Plans from $19 a month.