How to write prompts for Veo 3.1 Fast
Veo 3.1 Fast turns a sentence or a start picture into a short clip, with sound on request. The first two sections put Google’s own documents in our words, and we did not test them. The last rests on six short sample clips made with this model that we watched ourselves, a small sample.
Written from the provider’s documentation and from results we checked ourselves. Last checked November 8, 2026.
What Google says about Veo 3.1 Fast
From the provider’s documentation
- Google’s model page lists Veo 3.1 Fast with the same abilities as Veo 3.1: text to video, image to video, first and last frame, reference pictures, video extension and generated sound, in clips of 4, 6 or 8 seconds at 24 frames a second, in 16:9 or 9:16. The model page here shows what Pickshot offers for it.
- The difference the page documents is the top resolution: 4K for Veo 3.1, and 720p and 1080p for Veo 3.1 Fast. It states no difference in how the prompt is read. Google writes the prompt language as English.
- Google’s prompt guide covers its video models together and does not separate the two, so the advice below is the same for both.
Google’s prompt guide, in short
From the provider’s documentation
- You need not use every part of a prompt. Name a specific subject, give it a concrete action down to small gestures, set the place, the time of day and the weather, then add the viewpoint, the camera move, a lens effect, the style and the light.
- Keep a dolly, where the camera moves, apart from a zoom, where the lens changes. Google warns that some advanced angles and lenses are not officially supported, so results can vary.
- For a short clip, keep the change small and gradual, and use words for pace such as slow motion or time-lapse.
- For sound, say that you want it and write it in sentences of its own: an effect, the ambient noise, or dialogue with the speaker named. To leave something out, list it as a plain noun instead of writing no or don’t.
What our sample clips showed
From results we checked ourselves
- The lantern clip shows hundreds of lanterns over a river, silhouettes on the bank with their arms raised, a warm glow, and a camera that tilts up so the water sinks lower in the frame, as the prompt asked.
- The Hong Kong tram clip has a tram passing behind neon signs on a rain-wet crossing, but the woman under the umbrella holds the same place in the frame while it passes. We could not see her cross the street, as the prompt said.
- The guitar clip shows a young man playing an acoustic guitar at dusk, with city lights as soft dots over the water behind him. The framing is close on his hands and face, and the bench is not visible.
- The Bali clip shows rice terraces with mist and low sun. The prompt asked for a drone rising, and the movement is so slight that we could not tell a rise from a gentle drift.
- The bento clip shows hands placing a rolled omelette, green soybeans and cherry tomatoes into a round wooden box. The prompt asked for a top-down view, and the camera looks from a high angle, not straight down.
- The dim sum clip shows a hand lifting the lid and a thick plume of steam curling up, though it shows one stack of steamers where the prompt said baskets. We did not judge the sound of any clip.
Real results and the prompts behind them
Results made with this model. The prompts are shown exactly as written, in English.
Settings of this model
- De
- Tapez
- AI video model
- Mode de création
- Texte en vidéo · Image en vidéo
- Longueur
- 4–8s
- Résolution
- 720p / 1080p
- Aspect ratios
- 16:9 · 9:16
- Son
- Avec le son
- Prix
- from 168 / sec
Questions
Is Veo 3.1 Fast the same as Veo 3.1?
Google’s model page lists the same abilities for both and says the top resolution differs: 4K for Veo 3.1 and 1080p for Veo 3.1 Fast. We did not compare the two, and they have separate pages and guides here.
Can I write the prompt in Korean?
Google’s model page lists English as the prompt language, so write in English. We did not test other languages.
Why did my clip miss part of the prompt?
In our samples small details slipped: the woman did not cross the street, and a straight-down view came out at an angle. Google advises small, gradual change in a short clip, so ask for one clear action and look at the result.
Provider documentation we read
We read these pages and wrote the points that matter in our own words. The provider may change them.
- Veo prompt guide (Google Cloud) (docs.cloud.google.com)
- Veo 3.1 and Veo 3.1 Fast model page (Google Cloud) (docs.cloud.google.com)
More prompting guides
- How to write prompts for GPT Image 2.6 FlareAI image model
- How to write prompts for GPT Image 2.6 SunburstAI image model
- How to write prompts for Nano Banana 2.1AI image model
- How to write prompts for MOSS ImageAI image model
- How to write prompts for Grok Imagine ProAI image model
- How to write prompts for Nano Banana ProAI image model
- How to write prompts for Nano Banana 2AI image model
- How to write prompts for GPT Image 2.5 FlareAI image model
- How to write prompts for IndigoAI image model
- How to write prompts for SaffronAI image model
- How to write prompts for CeladonAI image model
- How to write prompts for LapisAI image model
- How to write edit requests for UmberÉditeur d’images IA
- How to write prompts for Kling Video 4.0AI video model
- How to write prompts for Seedance 2.5AI video model
- How to write prompts for Seedance 2.0 MiniAI video model
- How to write prompts for Kling V3AI video model
- How to write prompts for Kling O3 OmniAI video model
- How to write prompts for Veo 3.1AI video model
- How to write prompts for SilkAI video model
- How to write prompts for LacquerAI video model
- How to write prompts for SatinAI video model
Les noms de modèles, d’entreprises et de produits cités sur ce site sont des marques de leurs propriétaires ; Pickshot n’est ni affilié, ni sponsorisé, ni approuvé par ceux-ci.