Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
Input
Prompt
Overlapping geometric shapes, pulsing to upbeat electronic music with SFX of shifting patterns
Google DeepMind, formed in 2023 from Google Brain and DeepMind under Demis Hassabis, runs the Veo video-generation programme. Veo 3.1 Fast is the speed and cost tier of Veo 3.1, designed for high-volume creative iteration on Vertex AI, the Gemini API and consumer surfaces like VideoFX and YouTube Dream Screen. Like Veo 3 Fast before it, the Fast variant trades a small amount of fidelity for substantially faster generation and lower per-clip pricing, while keeping the joint audio-video diffusion stack and SynthID provenance from the full Veo 3.1.
Distilled latent video diffusion / DiT speed tier with joint audio-video diffusion
Veo 3.1 Fast is a distilled, low-step variant of Veo 3.1 that uses consistency-style sampler distillation and quantization to compress the diffusion process into far fewer denoising steps. The architecture is identical to Veo 3.1 -- a latent video diffusion model with a transformer denoiser plus a coupled audio diffusion module -- but parameters are tuned and the sampler shortened for substantially faster inference. Generation produces up to 8-second 1080p clips with synchronized audio (music, ambient sound, dialogue with lip-sync) at noticeably lower cost than the full Veo 3.1. Conditioning uses Gemini-family text encoders plus optional image and reference-frame inputs. Training is partly a distillation of Veo 3.1 with auxiliary supervision to preserve audio-video sync and prompt adherence under the shortened sampler.
Speed-tier Veo 3.1 with native synchronized audio retained
Up to 8-second 1080p clips at substantially lower latency and cost
Text-to-video and image-to-video
Reference-frame conditioning for consistency
Rich cinematographic prompt vocabulary
Multilingual prompts via Gemini text encoders
Available via Vertex AI, Gemini API, VideoFX, Whisk and YouTube Dream Screen
SynthID audio + visual watermarking
Best for: high-volume creative iteration, ad A/B testing, social shorts with audio.
Entraînement et licence
Distilled from Veo 3.1 over the same curated multilingual audio-video corpus; auxiliary supervision tuned for sampler-step efficiency and audio-video synchronization.
Licence: Proprietary commercial licence via Google Cloud / Vertex AI and Gemini API; commercial use under Google's generative-AI terms; mandatory SynthID watermark.
curl https://railwail.com/api/v1/videos/generations \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "veo-3-1-fast",
"prompt": "A slow drone shot over a misty pine forest at sunrise"
}'
# Response: {"job_id": "...", "status": "queued", ...}
# Poll until status is completed, failed or cancelled:
curl https://railwail.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAILWAIL_API_KEY"
import os
import time
import requests
API = "https://railwail.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['RAILWAIL_API_KEY']}"}
job = requests.post(
f"{API}/videos/generations",
headers=headers,
json={
"model": "veo-3-1-fast",
"prompt": "A slow drone shot over a misty pine forest at sunrise",
},
).json()
while True:
status = requests.get(f"{API}/jobs/{job['job_id']}", headers=headers).json()
if status["status"] in ("completed", "failed", "cancelled"):
break
time.sleep(5)
print(status["status"], status.get("output_url"))
const API = "https://railwail.com/api/v1";
const headers = {
Authorization: `Bearer ${process.env.RAILWAIL_API_KEY}`,
"Content-Type": "application/json",
};
const job = await fetch(`${API}/videos/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "veo-3-1-fast",
prompt: "A slow drone shot over a misty pine forest at sunrise"
}),
}).then((r) => r.json());
let status;
do {
await new Promise((r) => setTimeout(r, 5000));
status = await fetch(`${API}/jobs/${job.job_id}`, { headers }).then((r) => r.json());
} while (!["completed", "failed", "cancelled"].includes(status.status));
console.log(status.status, status.output_url);
Proprietary commercial licence via Google Cloud / Vertex AI and Gemini API; commercial use under Google's generative-AI terms; mandatory SynthID watermark.
