Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Vydra provides a unified API for AI image generation, video generation, and voice synthesis. It routes requests to models including Grok Imagine, Gemini, Flux, Veo 3, Kling, and ElevenLabs through a single API key and credit-based billing system. Agents can self-register and request billing activation without human setup.
A single API key and endpoint replaces separate accounts and integrations for six different AI media models.
When to use it
- Generating product mockup images from text prompts
- Editing an existing photo's background with a text instruction
- Creating short motion-controlled videos from a character image
- Converting article text to narrated audio for podcast drafts
- Automating image generation in an AI agent content pipeline
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate an image of a cyberpunk cityscape and read the description aloud
- 1POST to /models/grok-imagine with model: text-to-image and the prompt
- 2Extract imageUrl from the response
- 3POST to /models/elevenlabs/tts with the description text and a voice_id
- 4Receive the audio file URL from the response
An image URL and an audio file URL, both ready to download or embed
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.