The video generation API for developers. Programmatically create videos, images, voices, and avatars — or run end-to-end workflows via API or SDK.
VideoGen runs your entire generative media stack, so you can focus on building something people want.
Every request runs on the best AI model for the job. We benchmark flagship models on real workloads from 50k+ customers. Served from a global AI compute network.
Outputs are ready to embed, stream, or download with no extra setup — thanks to built-in storage, transcoding, and global CDN.
One API for video, images, speech, and avatars — call individual tools or run workflows like script-to-video or voiceover-to-video.
@videogen/sdk on npm and videogen on PyPI. Fully typed, auto-generated from our OpenAPI spec.
Webhooks and polling for production pipelines. Wire VideoGen into your CRM, CMS, or scheduled jobs.
Demo in 5 minutes, production-ready in 15 — via REST API, prebuilt SDKs, or our example projects.
CombinatorInstall the SDK and start generating videos immediately.
import { VideoGenClient, pollWorkflowRun } from "@videogen/sdk";
const client = new VideoGenClient({ token: "vg_..." });
const { workflowRunId, projectUrl } = await client.workflows.scriptToVideo({
script:
"Staying hydrated keeps your body and mind running at their best. Drinking enough water boosts your energy, focus, and mood. Keep a water bottle nearby and sip throughout the day.",
visualStyle: {
type: "AI_IMAGE",
aiStyle: "loose watercolor illustration with visible brushstrokes and soft color bleeds",
},
visualPacing: "MEDIUM",
quality: "HIGH",
remixActions: [
{ type: "ENABLE_CAPTIONS" },
{
type: "CONVERT_IMAGES_TO_VIDEOS",
motionPrompt: "slow cinematic push-in",
muteOutputVideos: true,
quality: "HIGH",
},
],
});
const run = await pollWorkflowRun(client, workflowRunId);
console.log(run.status, projectUrl);npm install @videogen/sdk“VideoGen solves the biggest pain points of video production—complexity, cost, and time.”
Garry Tan — CEO of Y Combinator