Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates images, audio, and video using MiniMax AI models via the MiniMax MCP server, then delivers the media to a Telegram chat. Uses the mcporter CLI to call MiniMax tools and the message action to send results with captions.
Combines media generation and delivery in a single workflow without manually downloading files and re-uploading them to Telegram.
When to use it
- Send AI-generated images to a Telegram group
- Generate TTS audio in Cantonese and deliver it via Telegram
- Create short AI videos and share them directly to a chat
- Clone a voice and send the result to a specific Telegram user
- Generate background music from lyrics and post it to Telegram
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate an image of a mountain at sunset and send it to my Telegram chat
- 1Call text_to_image with prompt 'mountain at sunset' and aspectRatio '16:9'
- 2Capture the full URL returned by MiniMax, including all query parameters
- 3Call message with action 'send', channel 'telegram', the target chat ID, the full media URL, and a caption
- 4Confirm delivery
The generated image appears in the specified Telegram chat with the provided caption
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.