Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Security fix: shell injection in assemble_mv.sh (filename escaping for ffmpeg concat lists), subtitle path escaping, python3 safe argv passing, SUNO_CALLBACK_URL restricted to https only
What This Skill Does
Generates complete music videos end-to-end: AI-composed music via Suno, AI-generated visuals from multiple providers, and final assembly with ffmpeg. Supports slideshow, video clip, hybrid, and Suno-native output modes. Tracks token-based costs per generation and auto-generates timestamped SRT lyrics for overlay.
Combines music generation, multi-provider visual generation, and video assembly into one scripted pipeline instead of requiring manual handoffs between separate tools.
When to use it
- Producing a K-pop style music video from a text prompt
- Creating a YouTube channel with a consistent vocal persona across tracks
- Generating a cheap slideshow MV for a demo track before committing to full video
- Prototyping music video concepts with dry-run cost estimates
- Assembling a final MP4 with burned-in lyrics from an existing audio file
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: '발라드 뮤비 만들어줘'
- 1Generates music with suno_music.sh using a ballad prompt and style, saving audio and lyrics.srt to outdir
- 2Plans 8-12 scene prompts from lyrics mood and saves them to prompts.json
- 3Runs gen_visuals.sh in slideshow mode with seedream image provider to generate scene images
- 4Runs assemble_mv.sh to combine audio and images with fade transitions, auto-overlaying lyrics.srt
- 5Reports final output path and total cost from cost_estimate.json
final_mv.mp4 with AI-generated ballad audio, AI images, and timestamped lyric subtitles
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.