https://varg.ai/sdk

varg.ai/sdk

  * GitHub
  * X.com
  * Discord

GitHub
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
[sdk-stripe]
Now in public beta

JSX for AI Video

Declarative programming language for Claude Code. AI Agent writes
JSX, you get videos.

bunnpmpnpmyarn
$bun install vargai ai
Star on GitHub
[sdk-demo-b]
portrait.tsx
{ ... }{ ... }{ ... }
portrait.mp4

Trusted by teams from

  * 
  * 
  * 
  * 
  * 
  * 

BUILT TO SCALE

Everything you need to generatecreate

[stripe-2]

Declarative

Describe WHAT you want, not HOW to make it. Just JSX that describes
your video structure.

[stripe-2]

Optimized for volumes

Everything just works out of the box. Same prompt = cache hit =
instant regeneration.

[stripe-2]

Flexible

Combine models into complex pipelines. Everything is composable.

Previous slideNext slide
AI Native

Made for AI Agents

AI agents write good varg-react code out of the box. The declarative
API maps naturally to how LLMs think about structure.

  * Agents generate correct code 95% of the time
  * Clear runtime errors for the other 5%
  * No magic strings or hidden state
  * Type-safe props catch mistakes early

Clear errors, easy fixes

For the 5% of cases where agents don't one-shot it, they receive
clear runtime errors with actionable messages. No cryptic stack
traces. No hidden state to debug.

$varg render scene.tsx
Error: Clip duration required when using Video
at Clip (line 12)
hint: add duration={5} or duration="auto"
# agent fixes and retries
$varg render scene.tsx
Rendering 3 clips...
Done! output/scene.mp4
CORE PRIMITIVES

16 components. Infinite possibilities.

A small, composable set of building blocks for assembling any video
pipeline -- from simple clips to full characters.

RenderClipImageVideoAnimateSpeechTalkingHeadMusicTitleSubtitle
CaptionsOverlaySplitSliderSwipePackshot

<Animate>

Breathe life into stills.

See it in action

Real patterns from production. Copy, paste, render.

Mirror SelfieSimple PortraitKawaii FruitsUGC TransformationTalking
Head
09-mirror-selfie.tsx

output.mp4

FAQ

/ What is Varg SDK?

TypeScript SDK that unifies AI video, image, voice, and music
generation under one API. Instead of learning five different SDKs,
you learn one. Comes with a unique JSX syntax for composing videos
declaratively -- write <Clip>, <Image>, <Speech> and get a rendered
MP4.

/ Do I need React?

No. The JSX syntax looks like React but doesn't use React at all.
It's a custom JSX runtime that transforms your components into FFmpeg
render instructions. You get the familiar developer experience
without the React dependency.

/ What runtime does it use?

Bun is the default and recommended runtime. Node.js works too, but
Bun gives you faster installs, native TypeScript, and better
performance. The SDK uses Bun-specific APIs like Bun.file() but falls
back gracefully.

/ Which AI providers are supported?

fal.ai (video, image, lipsync), ElevenLabs (voice, music), OpenAI
(Sora video), Replicate (1000+ models), and Higgsfield (character
generation). You only need API keys for providers you actually use.

/ How does caching work?

Every element gets a cache key based on its props. Generate an image
with prompt="sunset" -- it's cached. Render again with the same prompt
-- instant hit, no API call. Cache is content-addressed (like Git),
stored as files. Survives restarts. Saves real money on API costs.

/ Does it work in the browser?

No. The SDK requires FFmpeg for video composition, file system access
for caching, and server-side AI API calls. Use it in Node.js/Bun
servers, CLI tools, or serverless functions with FFmpeg layers.

/ How much does it cost?

The SDK itself: $0. Apache 2.0 license. You pay AI providers
directly: fal.ai ~$0.01-0.10/image, ~$0.50-2.00/video. ElevenLabs has
a free tier, ~$0.30/1K characters. Caching dramatically reduces costs
on iterative work.

/ How is this different from Remotion?

Different tools for different jobs. Remotion renders React
frame-by-frame -- great for motion graphics and data viz. Varg uses AI
generation + FFmpeg composition -- great for AI-generated content,
talking heads, and ads. Use Remotion for precise animations, Varg for
AI-powered content.

/ Can I use this with Next.js?

Yes, with constraints. Works in Server Components, API Routes, and
Server Actions. Does not work in Client Components, Edge Runtime, or
Vercel Serverless (FFmpeg + timeout limits). Best setup: separate
Node.js/Bun service for video rendering.

/ How fast is rendering?

Depends on what you generate. Image (Flux Schnell): 3-5s. Video
(Kling 2.5): 90-180s. Voice (ElevenLabs): 2-5s. FFmpeg composition:
5-30s. Cached element: <100ms. A 30-second video might take 3-5 min
first render, 10 seconds cached.

Vary & Generate. Scale.

bunnpmpnpmyarn
$bun install vargai ai
Star on GitHub

  * GitHub
  * X.com
  * Discord