Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
**Expanded model coverage and platform details with better integration notes.** - Added explicit support for IMA Video Pro (Sevio 1.0), IMA Video Pro Fast (Sevio 1.0-Fast), and clarified support for Sonic v5 music generation. - Updated platform description to emphasize unified access to all leading models (image, video, music, TTS). - Improved credential/environment details, including which endpoints use the API key and when. - Formalized persistence/logging retention and optional integration with ima-knowledge-ai documentation. - Enhanced clarity in model reference tables and introduced dynamic model availability guidance. - Minor keyword/description improvements for better discoverability and clarity.
What This Skill Does
Unified API gateway for generating images, videos, music, and speech through models like SeeDream, Midjourney, Wan, Kling, Veo, Sora, and Suno. Handles model selection, cross-media workflow orchestration, and user preference memory across eight task types including text-to-image, image-to-video, text-to-music, and text-to-speech.
Replaces juggling separate image, video, music, and TTS skills by routing all media generation through one API with intelligent model selection and preference memory.
When to use it
- Generate product photos with consistent character across multiple shots
- Create short promotional videos from text descriptions or reference images
- Produce background music that matches a video's mood and duration
- Convert written scripts or articles into spoken audio
- Build multi-step campaigns combining images, video, and soundtrack
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Make a product promo video of a puppy mascot with background music
- 1Generates a master reference image of the puppy using SeeDream 4.5
- 2Creates a video from the reference image using Wan 2.6 image-to-video
- 3Checks the video duration returned by the API
- 4Generates background music matching that duration using Suno
Video file URL and matching audio track URL, both delivered with cost and timing details
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.