Quoted Dialogue
Put spoken lines in quotation marks and tie each one to a character, for example: A woman says, "We have to leave now." Keep lines short enough to fit the clip. English is the language Google has fully tested.
Turn a prompt or a photo into an 8-second clip with its own dialogue and sound in 720p, 1080p or 4K, using the Veo 3.1 AI video generator.
The Veo 3.1 AI video generator renders picture and sound in the same pass, so voices, footsteps and room tone land on the right frame, in landscape or vertical.
Characters from Reference Images Give Veo 3.1 a face, an outfit and a location, and it places the same person in that setting with the styling intact.
Native Vertical Video Vertical clips are composed for a 9:16 screen from the first frame, ready for Reels, TikTok and Shorts.
Physical Motion in Imagined Worlds Spray, dust and suspension react to speed and weight, even when the hill is made of crystals.
First and Last Frame in Portrait Upload a start frame and an end frame, and Veo 3.1 fills the moment between them, here a hat going on in one natural gesture.
Direct speech, sound, framing and transitions with the Veo 3.1 AI video generator. Start from text, a photo, a pair of frames or up to three reference images.
Use the Veo 3.1 AI video generator for ads, social clips, short scenes and music content. Every clip arrives with its own sound, so it drops straight into an edit.
Add your packshot as a reference and describe the camera path, such as a fly-through from a window to the cans on a kitchen counter. The label stays readable, ready for product pages and paid social.
Describe the speakers, the street and what each one says, and you get a vox-pop clip with natural speech and matching lip movement. Switch to 9:16 for Reels, TikTok and Shorts, without booking talent.
Write the setting, the mood and a line of dialogue, and Veo 3.1 stages the scene with performance, music and city ambience. The result holds up in pitch reels, storyboards and short-form series.
Use a close-up of the singer and a crowd shot as first and last frames, then write the lyric in quotes. The camera arcs around the stage while she sings the line.
Place a model and an outfit on a black-sand beach or any location you describe. Wind, fabric and overcast light behave like an editorial shoot, ready for campaign teasers and lookbooks.
Ask for a handheld shot of a wok toss with a metallic clank and a sharp whoosh. Flame, steam and sizzle follow the motion, ready for menus, delivery listings and restaurant socials.
The Veo 3.1 AI video generator responds to film vocabulary, quoted speech and timed instructions.
Put spoken lines in quotation marks and tie each one to a character, for example: A woman says, "We have to leave now." Keep lines short enough to fit the clip. English is the language Google has fully tested.
Write each sound as its own cue, such as SFX: thunder cracks in the distance, or Ambient: the quiet hum of a starship bridge. Veo 3.1 places each one against the action.
Build prompts from five parts: cinematography, subject, action, context, and style and ambiance. Medium shot, a tired office worker, rubbing his temples, a cluttered 1980s office at night, grainy color film.
Split an 8-second prompt into segments such as [00:00-00:02] and [00:02-00:04], each with its own shot and sound. Veo 3.1 moves through them in order within one clip.
Say what each reference image is for, such as the detective, the woman and the office. Generate the next shot from the same set and faces, clothing and rooms stay consistent.
Choose 4, 6 or 8 seconds, 720p, 1080p or 4K, and 16:9, 9:16 or Auto. Turn sound off when you plan to score the clip yourself.
The Veo 3.1 AI video generator follows long, specific prompts, from shot type and lighting to timed actions and spoken lines.
Late night in a 1980s office
Medium shot of an exhausted office worker rubbing his temples beside a bulky 1980s computer in a cluttered office late at night. Harsh fluorescent overhead light and the green glow of a monochrome monitor. Retro look, shot on grainy 1980s color film.
Film noir reply
Using the reference images of the detective, the woman and the office, a shot focused on the woman. A faint, mysterious smile crosses her lips as she replies, "You were highly recommended." Black-and-white film noir.
Wax figure in timed beats
A small pale-yellow wax figure holds a flame in a landscape of molten wax, a dripping candle to its left. 0-1s: eye-level tracking shot as it starts to walk, feet rippling the wax. 1-7s: slow, deliberate steps, arm raised to guard the flame. 7-8s: the camera eases back to reveal the wider wax world.
Mid-air leap with a dolly move
The camera dollies around a woman suspended mid-leap in a long, sterile, monochrome green corridor. Her dark trench coat and trousers billow, arms outstretched, her profile set with focus. High-tension cinematic scene.
Two-host animal podcast
A monkey and a polar bear host a casual podcast, a tropical jungle behind one and an arctic glacier behind the other. Monkey: "Welcome back to Bananas and Ice! I am Banana." Polar bear: "And I'm Ice!"
Tracking shot into a bar
Slow track along iridescent tiled walls above still water, then a push-in and a turn that reveals a curved bar and a finished cocktail. Soft jazz, clinking ice. "Welcome," a smooth voice says. "Care for a taste?" A black cat jumps onto the bar.
Generate a Veo 3.1 clip in three steps
Step 01
Upload a photo to animate, two frames to connect or up to three reference images.
Step 02
Write the shot, the action and the sound. Put dialogue in quotes.
Step 03
Pick 4, 6 or 8 seconds, a resolution and a ratio, then generate and download.
Start with a sentence, a photo or two frames. Generate a clip with its own dialogue and sound, run as many takes as you need and download the one you want in 720p, 1080p or 4K.
Upgrade or cancel anytime. Choose a plan for clean output, fast generation, full model access and priority support.
Monthly
Annual
Quick answers about Veo 3.1, plus the plans, credits and billing behind it on ImgVid.