Skip to main content

​
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 IDInputSpeedCredits~Cost
veed-fabric-1.0Image + audio~30-50s100$1.00

​
Quick start

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)

​
Parameters

​
files
array
required
Two files: one image (portrait) and one audio (speech). The gateway auto-detects file types by extension.
​
provider_options
object
resolution — "480p" or "720p" (defaults to "720p").
VEED Fabric doesn’t use a prompt or duration parameter. The video length matches the audio duration.

​
Pricing

ModelCreditsUSD
veed-fabric-1.0100$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.

Sync V2 Pro

Higher quality lipsync. Requires video input instead of image.

OmniHuman

Full-body animation from image + audio.

ElevenLabs

Generate the speech audio to pair with VEED Fabric.