# Veo > Google's Veo 3.1 Fast on Zurelay: 8 second 720p clips with dialogue and sound, from a prompt or a start image. Source: https://zurelay.com/docs/veo Google’s Veo 3.1 Fast: 8 second 720p clips with dialogue, sound effects and ambient sound, from a prompt or a start image. ## Prices | Model | Resolution | Per second | 8 second clip | | --- | --- | --- | --- | | [Veo 3.1 Fast](https://zurelay.com/models/veo-3.1-fast) | 720p | $0.025 | $0.20 | A clip costs its length times the rate: a 8 second 720p clip is $0.20. It’s charged only when the video is delivered. ## What it takes - A prompt of up to 8,000 characters. - A `first_frame` to animate. No reference images. - Lengths from 8 to 8 seconds, in whole seconds. - 16:9 and 9:16. From a first frame, leave out `aspect_ratio` and the clip takes the image’s shape: 9:16 for a portrait image, 16:9 otherwise. - Sound is always on. - 720p. ## Example Request body: ```json { "model": "veo-3.1-fast", "first_frame": "https://example.com/presenter.jpg", "prompt": "She holds up the serum bottle, smiles and says: \"Two weeks with this serum and my skin is glowing.\" Handheld phone video, soft window light." } ``` ## Prompting - Describe the shot, the motion and the camera, then the sound: who says what, in quotes, and the effects. - From a start image, describe what happens next: the motion, the camera and the sound. - Google supports English prompts best. ## Good to know - Clips usually take one to two minutes. - Every clip is 8 seconds at 720p, so you can leave out `seconds` and `resolution`. - There’s no end frame (clips made with one carry a visible Veo mark), negative prompt or seed. Clips carry Google’s invisible SynthID watermark, and no visible one. - Prompts or images that may break the content rules can be declined (`content_policy`); declined videos are free. - Videos are kept for 30 days; download the ones you want to keep. Full API details: [Video generation](https://zurelay.com/docs/video). Try it in the dashboard’s [Playground](https://zurelay.com/app/playground), which shows the code for each video.