OpenClaw Venice.ai Media Plugin

Image and video generation for OpenClaw using Venice.ai API.

Features

• 🎨 80+ image models — flux-2-max, venice-sd35, gpt-image-2, recraft-v4-pro, and more
• 🎬 80+ video models — LTX, WAN, Kling, Veo, Sora, Runway Gen-4, and more
• 🔐 Uses bundled Venice auth — no separate API key needed
• 📐 Multiple sizes — various aspect ratios for images and video
• ⏱️ Video duration & FPS control

Prerequisites

• Venice.ai API key — get one at https://venice.ai/settings/api
• The plugin uses the bundled Venice provider for authentication

Installation

From ClawHub (recommended):

openclaw plugins install openclaw-venice-media

From source:

git clone https://github.com/acwilan/openclaw-venice-ai.git
cd openclaw-venice-ai
npm install
npm run build
openclaw plugins install "$(pwd)"

Authentication

This plugin uses the bundled Venice provider for authentication:

openclaw models auth setup-token --provider venice

Configuration

Add to your ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "venice-media": {
        "enabled": true,
        "config": {
          "defaultImageModel": "flux-2-max",
          "defaultVideoModel": "ltx-2-fast-text-to-video",
          "defaultImageSteps": 40,
          "defaultImageCfgScale": 8.0,
          "defaultVideoDuration": 5,
          "defaultVideoFps": 24,
          "hideWatermark": true,
          "safeMode": false,
          "outputDir": "~/Downloads/venice-ai-output"
        }
      }
    }
  },
  "agents": {
    "defaults": {
      "imageGenerationModel": {
        "primary": "venice-media/flux-2-max"
      },
      "videoGenerationModel": {
        "primary": "venice-media/ltx-2-fast-text-to-video"
      }
    }
  }
}

Config Options

Usage

Image Generation

Generate an image of a sunset over mountains

Video Generation

Generate a video of waves crashing on a beach

Note on video size: Venice.ai videos can be large. For Telegram (5MB limit), use:

• Lower resolution (480P) with resolution parameter
• Shorter durations (6s is minimum, works for most models)
• Example: Generate a 480P video of ...

Or specify models:

Generate an image with venice-media/recraft-v4-pro of a cyberpunk city
Generate a video with venice-media/kling-2.6-pro-text-to-video of a rocket launch

Available Models

Image Models (30+)

Video Models (80+)

See Venice.ai docs for full list: https://venice.ai/docs

License

MIT © Andres Rovira