How to prompt Veo 3 for the best results

How to prompt Veo 3 for the best results – Replicate blog

Replicate Blog

How to prompt Veo 3 for the best results

Posted June 10, 2025 by shridharathi fofr

Ready to give it a spin? Try Veo 3

Google’s Veo 3 generates videos with audio from text prompts. The audio can be dialogue, voice-overs, sound effects and music.

Let our resident AI podcaster introduce us:

Prompt: A podcast show, a woman in a grey sweater and dark brown tousled hair in an updo, she looks directly at the camera, with strands framing her face. She talks into a mic saying: This is Replicate’s guide to prompting Veo 3… Write what happens

First the basics. A well-crafted prompt is the key to generating good videos. The more you can specify in your prompt, in plain language, the easier it is for Veo 3 to understand and generate the video you want.

Try to include these visual elements in your prompt:

Subject: Who or what is in the scene — a person, animal, object, or landscape.

Context: Where is the subject? Indoors? A city street? A forest?

Action: Is your subject walking, jumping, turning their head?

Style: The visual aesthetic you’re aiming for (cinematic, animated, stop-motion, etc).

Camera motion: Describe how the camera moves: aerial shot, eye-level, top-down, or low-angle.

Composition: How the shot is framed: wide shot, close-up, etc.

Ambiance: Mood and lighting. You can say things like “warm tones,” “blue light,” or “nighttime.”

You also need to include audio elements, which we’ll cover in more detail below.

Here’s an example of a basic prompt versus a detailed one:

A man answers a rotary phone

Versus:

A shaky dolly zoom goes from a far away blur to a close-up cinematic shot of a desperate man in a weathered green trench coat as he picks up a rotary phone mounted on a gritty brick wall, bathed in the eerie glow of a green neon sign. The zoom reveals the tension and the desperation etched on his face as he struggles to talk on the phone. The shallow depth of field focuses on his furrowed brow and the black rotary phone, blurring the background into a sea of neon colors and indistinct shadows, creating a sense of urgency and isolation.

The second prompt contains structural elements to nudge Veo 3 towards the scene we are trying to create.

Your browser does not support the video tag. Basic prompt Your browser does not support the video tag. Detailed prompt

Change your prompt each time

If you’re familiar with prompting models like Midjourney or Flux , you’ll know that with those models you’ll get a decent level of variation if you run the same prompt a few times (ie using different seeds).

Veo 3 is different. For the same prompt, even one that’s fairly simple, Veo 3 will output very similar results. You might get the same looking person in the same clothes, in a similar sort of place. This is excellent if you’ve had an output that has a slight error, like a coherency or audio glitch – you can run a different seed and get what you want. But if you’re in discovery mode, when you want to see a range of what’s possible, then running the same prompt multiple times is a waste of your money.

In the example below we ran the prompt “a woman laughs” twice, with different seeds. Note how she looks the same, she’s wearing the same clothes, she laughs in the same way, the room is the same, she’s even wearing the same earrings. It’s unusual for a model to be this consistent.

First video Second video

If you’re not sure what you want yet, start with a few broadly different prompts. If you know elements of what you want, then be specific about those.

In this video the obvious things we could do are begin to play with descriptions for:

how the woman looks (hair color, hair style, skin color)

what she’s wearing

where she is

how she is laughing

why she is laughing

Here are a couple of examples:

a woman laughs long and loudly, she’s in an office meeting and she’s embarrassed afterwards a woman laughs quietly, she’s at home watching a tv show

Character consistency

Typically character consistency is hard when you’re using a video model without a starting frame or scene ingredients. These features are coming to Veo 3 soon.

In the meantime, because similar prompts yield similar characters, if you keep a character’s detailed prompt description consistent across generations, you’ll often get someone who looks the same. This means you can keep a list of character descriptions and repeat them verbatim across different prompts:

John, a man in his 40s with short brown hair, wearing a blue jacket and glasses, looking thoughtful

The more unique and specific these descriptions, the better Veo 3 maintains visual continuity between separately generated scenes. Create character reference sheets with exact wording to ensure consistency.

John, a man in his 40s with short brown hair, wearing a blue jacket and glasses, looking thoughtful, he says: Hello, I am also John, and I look kind of the same as that guy over there (no subtitles!). He is in a bright light room. John, a man in his 40s with short brown hair, wearing a blue jacket and glasses, looking thoughtful, he says: Hello, my name is John, I am a character invented for this blog post (no subtitles!)

Prompting audio

As Veo 3 generates audio with each video, you also need to prompt for the audio you want to hear. Consider these elements:

What people are saying (dialogue)

The ambient noise of the scene (the sounds of a busy street, a busy office, a busy cafe, etc)

Sound effects or noises from outside the scene (like a phone ringing)

Any music the scene might need (a tense cinematic score, a cheerful pop song, etc).

Prompting dialogue and avoiding subtitles

The characters you can create with Veo 3 are fascinating. They talk, tell jokes, gesticulate, sometimes they can act. But if you want them to talk, you need to prompt for that.

You can prompt dialogue in two different ways:

Explicitly: “A guy says: My name is Ben”

Implicitly: “A guy tells us his name”

Both of these will lead to a video of a guy talking, the first will use the exact words you asked for, the second will let the model decide how to say it, in this case the model will decide on a name for you.

Writing your own dialogue

If you’re being explicit about what’s being said, try to keep your dialogue short. It should be something that can be said in just about 8 seconds.

If you try to pack too much in, then you can end up with a character that’s speaking way too fast. If you ask…