Your agent writes the cut as code, while Grok Imagine, ElevenLabs, and Cloudflare generate assets inside the script. What you get isn’t a lucky clip — it’s a program you can edit, version, and re-run.
Structure-first video that scales like software — never one-shot prompts.
Free to start — every new account gets $2 in credit. No card required. Works in Claude, Cursor, Aider, OpenCode, and Codex.
The future
is compiled
00:04.2 / 00:06.5
Fig. 01 — A compiled reel. Clips are written in VidScript, generative assets resolve at compile time, and the timeline stays reproducible.
Intent becomes VidScript. Generative models execute as functions inside the script. The compiler produces deterministic, reproducible video.
Describe the video or give your agent a brief. No blank timelines.
Your agent writes readable, versionable code using templates and brand rules.
Imported package functions like xai.imagine(), cf.genVideo(), cf.image(), eleven.music(), and xai.tts() run inside the script. Pick any Cloudflare Gateway model with model:.
The compiler enforces timing, shaders, overlays, and audio mixing. Output is reproducible.
import cf from "@scenerok/cloudflare"
import xai from "@scenerok/xai"
input brand = "https://cdn.scenerok.com/samples/brand-hero.mp4"
# Generative assets created at compile time — pick any Cloudflare Gateway model
[-] = video cf.imagine("minimal product shot, floating in void, soft rim light", model: "pixverse/v6", aspect_ratio: "9:16", duration: 6)
[0s .. 6.5s] = video brand
[0.8s .. 5.8s] = audio xai.tts("This is not generated. This is compiled.", voice: "jessica")
output to "launch-reel.mp4", resolution: "1080x1920"Web editor first
CLI + MCP + Skills
Templates + version control
Call frontier models as first-class functions inside VidScript. They run at compile time. You keep full control over timing, composition, and brand rules.
Generative assets are created at compile time — the timeline itself stays declarative, diffable, and repeatable.
import xai from "@scenerok/xai"
import motion from "@scenerok/basic-animations"
[-] = video xai.imagine("cyberpunk city at dusk, cinematic", aspect_ratio: "9:16", duration: 4.2)
[2.8s .. 7s] = text "The future is compiled", style: title, animate: motion.fadeIn(0.6s)import cf from "@scenerok/cloudflare"
import motion from "@scenerok/basic-animations"
[-] = video cf.imagine("luxury product macro, studio rim light", model: "google/veo-3.1-fast", aspect_ratio: "9:16", duration: 6)
[-] = video cf.image("matching hero still", model: "black-forest-labs/flux-2-pro-preview", aspect_ratio: "9:16")
[0.4s .. 6s] = text "One plugin. Many providers.", animate: motion.fadeIn(0.5s)import xai from "@scenerok/xai"
import eleven from "@elevenlabs/music"
let voice = xai.tts("This is not a prompt. This is a program.", voice: "jessica")
let score = eleven.music("dark electronic tension, 90bpm", duration: 18)
[0s .. 18s] = audio voice
[0s .. 18s] = audio score, volume: 0.35VidScript covers the common video editing actions — layering shots, cutting and timing, sound, on-screen text, and exporting. Describe what you want and it shows up in the finished video, exactly as written.
Stack shots and set the mood
Put every moment in the right place
Keep the audio clean and balanced
Say it on screen
Build once, deliver anywhere
SceneRok renders HyperFrames — the open HTML + CSS + GSAP → MP4 format — one frame at a time. This is how frontier models work now: they write the creative HTML, and SceneRok turns it into reproducible video that composites over real footage and WebGL.
Call animations.custom_html() with inline HTML, a URL, a local file, or an uploaded asset. Model-generated or hand-authored — it runs through the same deterministic pipeline as everything else.
import animations from "@scenerok/animations"
# Model-authored HTML — rendered frame-by-frame into your MP4
[0s .. 5s] = animations.custom_html(
html: "<!doctype html>...", designWidth: 1920, designHeight: 1080,
title: "Q3 Launch", accent: "#3b82f6")
# Or call a ready-made block from the HyperFrames catalog
[5s .. 12s] = animations.code_morph("const a = 1", "const a = 2", theme: "monokai")
[12s .. 17s] = animations.x_post("SceneRok", "@scenerok", body: "HTML -> MP4")77 ready-made blocks you call from VidScript: code animations, terminal and VS Code snippets, lower-thirds, social posts, kinetic text, and iOS liquid glass.
HTML layers mount beside the Three.js canvas — an iframe for isolated scenes, inline for overlays that blend with the frame beneath.
No randomness and no network at render time. The host seeks every frame, so the same source always yields the same MP4.
The Cloudflare media plugin routes image and video generation through Cloudflare AI Gateway and Unified Billing. Use curated first-class models or pass any gateway model id with model:.
Defaults: pixverse/v6 for text-to-video and black-forest-labs/flux-2-pro-preview for stills. Call cf.listModels() from VidScript to inspect the full catalog at compile time.
PixVerse v6 text/image-to-video, 1-15s, audio optional, up to 1080p.
PixVerse v5.6 text/image-to-video, 1-15s, audio optional, up to 1080p.
Vidu Q3 Pro text/image/start-end-frame video, 1-16s, audio optional.
Vidu Q3 Turbo lower-latency text/image/start-end-frame video, 1-16s.
Runway Gen-4.5 text/image-to-video, 2-10s, ratio-specific output sizes.
MiniMax Hailuo 2.3 text/image-to-video with realistic motion and VFX.
ByteDance Seedance 2.0 multimodal video, 4-12s, audio optional.
Google Veo 3.1 video, fixed 4s/6s/8s durations, audio optional.
Google Veo 3.1 Fast lower-latency video, fixed 4s/6s/8s durations.
Google Veo 3 Fast lower-latency video, fixed 4s/6s/8s durations, audio optional.
xAI Grok Imagine Video through Cloudflare Unified Billing.
xAI Grok Imagine Video 1.5 preview through Cloudflare Unified Billing.
Alibaba Wan 2.7 image-to-video, 2-15s, 720P/1080P.
Real placeholder semantics. Versioned. Forkable. Parameterized. Dynamic slots can be filled by generative calls, external data feeds, or human input — while brand rules, timing structures, and visual systems remain enforced by the template.
Drop in new assets or let cf.imagine(), xai.imagine(), and eleven.music() populate the slots.
Drop in new assets or let cf.imagine(), xai.imagine(), and eleven.music() populate the slots.
Drop in new assets or let cf.imagine(), xai.imagine(), and eleven.music() populate the slots.
Drop in new assets or let cf.imagine(), xai.imagine(), and eleven.music() populate the slots.
Local preview + Vast.ai / Jarvis Labs GPU for final renders. Same source, different targets.
One balance for traditional renders and generative plugin calls (Grok Imagine, Cloudflare Gateway models, ElevenLabs). Transparent pricing.
Every video is code. Diff it. Version it. Reproduce it. No more "final_v7_reallyfinal.mp4".
Every render and every generative call is logged against your balance. Full reproducibility. No black boxes.
Install the SceneRok CLI and skills once. Then work entirely through Claude, Cursor, Aider, or Codex.
Free to start — new accounts get $2 in credit. No card required.
One command in your agent: Read the SceneRok skill and create a launch reel