Veo 3.1 Fast AI Video Generator

Turn text, one image or a first and last frame into a 4-, 6- or 8-second Veo 3.1 Fast video at 720p or 1080p, sound optional. See the credit quote first.

  • From 100 credits per clip
  • Text to video / Image to video / First + last frame
  • 4s / 6s / 8s
  • 720p
  • Audio available
Model

Veo 3.1 Fast

Browse by task
Input

What scene would you like to create?

Choose a scene to fill in the subject, setting and motion. No image upload needed. These are editable prompt drafts, not recorded outputs.

Prompt0/1794
More prompt ideas
More settings · 16:9 · 6s
Aspect ratio
Duration
Resolution
Audio

Checking generation and private storage configuration.

This page runs Veo 3.1 Fast. Standard Veo 3.1 isn’t offered or billed here.

Billing and delivery

Generate charges the displayed quote for the current model, duration and audio choice. If generation fails or the file fails our check, the credits come back automatically; a finished clip you don’t like is still charged. Finished clips stay in My videos.

Estimated cost: 150 credits
Sign in to generate

Sample result

8s · MP4
A paper island, drifting clouds.Made on Cicadas · Veo 3.1 Fast · 8s
Use this recipe

About Veo 3.1 on Cicadas

Veo 3.1 Fast turns a prompt, one image, or an opening and closing frame into a 4-, 6- or 8-second video at 720p or 1080p, with sound if you want it. Only the Fast version of Veo 3.1 runs here, not the standard model. Watch the five example clips, choose your settings and see the exact credit quote before you submit; each successful video is a private MP4 in My videos.

Veo 3.1 examples made on Cicadas

First + last frame8s · 720p

A paper island, drifting clouds.

An eight-second Veo scene using the same paper landscape for both endpoints. Clouds cross the island; inspect the join before using it as a loop.

Use this recipe ↗
Text to video6s · 720p

Give the scene a sound.

A wide desert shot with generated sound. The recorded audio has footstep-like taps and a low thump; it does not establish exact environmental sound control.

Use this recipe ↗
Image to video6s · 720p

A product worth watching.

Give your product photo a slow orbit, sculpted light and a little drama.

Use this recipe ↗
Text to video4s · 720p

Flames in the pan.

Veo 3.1 Fast at 720p with audio, 4 seconds. A cook tosses vegetables in a cast-iron pan and a burst of flame rises, in a close side shot. The audio has sizzling and running water.

Use this recipe ↗
Text to video4s · 720p

Walking home in the rain.

Veo 3.1 Fast at 720p with audio, vertical, 4 seconds. A figure with a clear umbrella walks away down a rainy neon street, reflections shimmering on the road. The audio is splashing rain and water.

Use this recipe ↗
Text to video8s · 720p

Glass kiwi, sliced.

Veo 3.1 Fast, 8 seconds, 9:16, with sound. A knife cuts one slice off a translucent kiwi, which falls flat onto the board; a hand steadies the fruit. Our listener heard a thump and a light clatter rather than the crisp glassy crunch the prompt asked for.

Use this recipe ↗
Text to video8s · 720p

Kinetic sand, cut.

Veo 3.1 Fast, 8 seconds, 9:16, with sound. A palette knife slices into a purple sand cube and a slab crumbles onto the tray, with rustling and crackling and no music. It cuts one thick slab rather than several thin slices.

Use this recipe ↗
Text to video8s · 720p

Bigfoot’s morning vlog.

Veo 3.1 Fast, 8 seconds with sound, vertical. Bigfoot holds the camera at arm’s length in a sunlit pine forest and says the whole line word for word, with footsteps and heavy breathing under it.

Use this recipe ↗
Text to video8s · 720p

Pancakes, don’t tell the rangers.

Veo 3.1 Fast, 8 seconds with sound, vertical. Bigfoot flips a blueberry pancake over the fire and whispers “Don’t tell the rangers”; the second sentence of the line is not spoken.

Use this recipe ↗
Text to video8s · 720p

Two cats, one mic.

Veo 3.1 Fast, 8 seconds with sound, vertical. Two original cartoon cats rap both written lines word for word over a hip-hop beat with scratches; partway through, the shot cuts from a wide view to a closer one.

Use this recipe ↗

Why use Cicadas for Veo 3.1

Make a Veo 3.1 Fast video from text or one image

Write a prompt, or animate one JPG, PNG or WebP you're allowed to use. Pick landscape or portrait framing and describe one continuous shot.

Connect a first and last frame with Veo 3.1 Fast

Upload an opening frame and a closing frame, and Veo 3.1 Fast connects them in one clip. Each required image is checked before you submit, and the mode you chose is saved with the job.

Pick 4, 6 or 8 seconds at 720p or 1080p, sound optional

Length and sound change the credit quote, while 1080p currently costs the same as 720p. You see the exact total before you submit, and each successful video is a private MP4 you can download or find in My videos.

How to use Veo 3.1

  1. 01

    Choose text, one image, or a first and last frame. Upload only JPG, PNG or WebP images you're allowed to use.

  2. 02

    Describe one continuous shot, then set 4, 6 or 8 seconds, 720p or 1080p, landscape or portrait, and sound on or off.

  3. 03

    Check the exact credit quote and generate. Watch the full MP4 for motion, structure, sound and, in frame mode, how smoothly it links your two frames. Then download it or find it later in My videos.

Veo 3.1 prompt ideas

Copy one into the prompt box above and adapt it to your shot. Or write your own shot by shot in the prompt generator.

  • “A fictional adult traveler stands on a wide desert ridge at dawn. Slow forward camera movement, distant mist, natural wind and cloth rustling, no dialogue or music, one continuous cinematic shot.”

  • “An unbranded ceramic desk lamp on a walnut table turns on as warm light spreads across the surface. Locked camera, stable product shape, one continuous shot, no text or logos.”

  • “A quiet alpine lake at sunrise. Thin mist crosses the water while small ripples catch warm light. Slow controlled push-in, realistic natural motion, one continuous shot.”

Veo 3.1 FAQ

Tested on Cicadas · reviewed 2026-09-30

Five recorded Veo 3.1 Fast clips: three from text with audio (one 6 seconds, two 4 seconds, all 720p), one image without audio (6 seconds, 720p) and a first/last-frame transition (8 seconds, 720p, silent). They do not show standard Veo 3.1 quality, and speech timing is not guaranteed.

Updated Sep 29, 2026 · How we test