> ## 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.

# VEED Fabric

> Fast talking head generation from a single image and audio — simplest lipsync pipeline

## Overview

VEED Fabric 1.0 generates talking head videos from a single portrait image and an audio file. It's the simplest lipsync pipeline — no video input needed, just image + audio.

| Model ID          | Input         | Speed    | Credits | \~Cost |
| ----------------- | ------------- | -------- | ------- | ------ |
| `veed-fabric-1.0` | Image + audio | \~30-50s | 100     | \$1.00 |

## Quick start

<CodeGroup>
  ```typescript SDK theme={null}
  import { createVarg } from "vargai/ai"

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

  const result = await varg.videoModel("veed-fabric-1.0").generate({
    imageUrl: "https://example.com/portrait.jpg",
    audioUrl: "https://example.com/speech.mp3",
  })

  console.log(result.video.url)
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.varg.ai/v1/video \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "veed-fabric-1.0",
      "prompt": "",
      "files": [
        { "url": "https://example.com/portrait.jpg" },
        { "url": "https://example.com/speech.mp3" }
      ]
    }'
  ```
</CodeGroup>

## Parameters

<ResponseField name="files" type="array" required>
  Two files: one image (portrait) and one audio (speech). The gateway auto-detects file types by extension.
</ResponseField>

<ResponseField name="provider_options" type="object">
  `resolution` — `"480p"` or `"720p"` (defaults to `"720p"`).
</ResponseField>

<Note>
  VEED Fabric doesn't use a prompt or duration parameter. The video length matches the audio duration.
</Note>

## Pricing

| Model             | Credits | USD    |
| ----------------- | ------- | ------ |
| `veed-fabric-1.0` | 100     | \$1.00 |

## Tips

* **Simplest pipeline for talking heads.** Image + audio = talking video. No intermediate video step needed.
* **Use with ElevenLabs speech** — generate narration with `eleven_v3`, then animate with VEED Fabric.
* **720p recommended** for quality. 480p is faster but noticeably lower resolution.
* **Portrait images work best.** Front-facing, well-lit, neutral expression for cleanest results.

## Related models

<CardGroup cols={2}>
  <Card title="Sync V2 Pro" icon="lips" href="/models/lipsync/sync">
    Higher quality lipsync. Requires video input instead of image.
  </Card>

  <Card title="OmniHuman" icon="person" href="/models/lipsync/omnihuman">
    Full-body animation from image + audio.
  </Card>

  <Card title="ElevenLabs" icon="microphone" href="/models/speech/elevenlabs">
    Generate the speech audio to pair with VEED Fabric.
  </Card>
</CardGroup>