> ## Documentation Index
> Fetch the complete documentation index at: https://docs.varg.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# varg

> AI video generation platform. Install the skill, prompt your agent, get videos.

## What is varg?

varg is an AI video generation platform. Install the skill, set your API key, and let your AI agent create videos — with images, voiceover, music, lipsync, and captions.

```bash theme={null}
# 1. Install the varg skill
npx -y skills add vargHQ/skills --all --copy -y

# 2. Set your API key (get one free at app.varg.ai)
export VARG_API_KEY=varg_live_xxx

# 3. Create your first video
claude "create a 10-second product video
  for white sneakers, 9:16, UGC style,
  with captions and background music"
```

Under the hood, the agent writes declarative JSX code like React components, and varg handles AI generation, caching, and video rendering. One API key, one gateway, all providers.

<Accordion title="What the generated code looks like">
  ```tsx theme={null}
  /** @jsxImportSource vargai */
  import { Render, Clip, Image, Video, Speech, Captions, Music } from "vargai/react"
  import { createVarg } from "vargai/ai"

  const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

  const character = Image({
    model: varg.imageModel("nano-banana-pro"),
    prompt: "cute orange cat character, round body, big eyes, Pixar style",
    aspectRatio: "9:16",
  })

  const voiceover = Speech({
    model: varg.speechModel("eleven_v3"),
    voice: "josh",
    children: "Hey everyone! Let me show you something cool.",
  })

  export default (
    <Render width={1080} height={1920}>
      <Music prompt="upbeat electronic" model={varg.musicModel()} volume={0.1} />
      <Clip duration={5}>
        <Video
          prompt={{ text: "cat waves hello, bounces happily", images: [character] }}
          model={varg.videoModel("kling-v3")}
        />
      </Clip>
      <Captions src={voiceover} style="tiktok" color="#ffffff" withAudio />
    </Render>
  )
  ```
</Accordion>

## Quick Start

<Steps>
  <Step title="Get your API key">
    Sign up at [app.varg.ai](https://app.varg.ai) and copy your API key.
  </Step>

  <Step title="Install the varg skill">
    ```bash theme={null}
    npx -y skills add vargHQ/skills --all --copy -y
    ```

    This gives Claude Code, Cursor, Windsurf, and 40+ other agents full varg context.
  </Step>

  <Step title="Set your API key">
    ```bash theme={null}
    export VARG_API_KEY=varg_live_xxx
    ```
  </Step>

  <Step title="Create a video">
    Ask your AI agent:

    *"Create a 10-second TikTok video of a cute robot waving hello with upbeat music and captions"*
  </Step>
</Steps>

## Why varg?

<CardGroup cols={2}>
  <Card title="One API Key" icon="key">
    Single `VARG_API_KEY` for images, video, speech, music, and lipsync. No juggling provider keys.
  </Card>

  <Card title="Declarative JSX" icon="code">
    Write videos like React components. Compose scenes, add transitions, layer audio.
  </Card>

  <Card title="AI-Native" icon="wand-magic-sparkles">
    Built-in support for Kling, Seedance, Flux, ElevenLabs, Wan, and more. All through one gateway.
  </Card>

  <Card title="Automatic Caching" icon="bolt">
    Same props = instant cache hit at \$0. Re-render videos without re-generating AI assets.
  </Card>
</CardGroup>

## Use Cases

* **Social Media Content**: TikTok, Reels, Shorts at scale
* **Talking Characters**: AI avatars with lipsync and captions
* **Product Videos**: E-commerce showcases, before/after transformations
* **Slideshows**: Image sequences with transitions and music

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart Guide" icon="rocket" href="/quickstart">
    Full setup in 2 minutes
  </Card>

  <Card title="Authentication" icon="key" href="/authentication">
    API keys, login, billing
  </Card>

  <Card title="Templates" icon="clone" href="/templates">
    Copy-paste examples for common video types
  </Card>

  <Card title="Cloud Render API" icon="cloud" href="/render-api">
    Submit TSX via API — zero local dependencies
  </Card>
</CardGroup>