LaunchKit · 2026
Back to Skills

remotion-excalidraw-tts

Generate a narrated Remotion video from an Excalidraw (.excalidraw) diagram using text-to-speech (macOS say)

0
834 downloads
by @jack4world

Setup & Installation

openclaw skills install @jack4world/remotion-excalidraw-tts

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install remotion-excalidraw-tts

Version History

v1.1.0Feb 9, 2026 - Version note by skill developer:

Add OpenAI + ElevenLabs TTS backends; support external storyboard.json to drive camera/focus/subtitles

What This Skill Does

Converts an Excalidraw diagram and a text script into a narrated MP4 video. Uses macOS `say`, OpenAI TTS, or ElevenLabs for voiceover, and Remotion for rendering. Supports pan/zoom camera moves and focus highlights via a storyboard JSON.

Combines diagram rendering, TTS, and video composition in a single CLI command instead of requiring manual screen recording or video editing software.

When to use it

  • Turn architecture diagrams into walkthrough videos
  • Create narrated explainer videos from whiteboard sketches
  • Automate voiceover generation for technical presentations
  • Produce pan/zoom highlight reels over system design diagrams
  • Batch-render multiple diagram videos from CI or scripts

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: make a narrated video from my system-design.excalidraw with voiceover.txt

AGENT
  1. 1Receives --diagram, --voiceover-text, and --out paths
  2. 2Copies Remotion template into a temp working directory
  3. 3Generates voiceover.mp3 from the text file using macOS say
  4. 4Sets Remotion composition duration to match audio length
  5. 5Runs npx remotion render and writes the final MP4
OUTPUT

Rendered MP4 file at the specified output path with synchronized narration and diagram visuals

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

OPENAI_API_KEY environment variable (only if using OpenAI TTS backend)ELEVENLABS_API_KEY environment variable (only if using ElevenLabs TTS backend)macOS (required for say TTS backend)ffmpeg and ffprobe installed on the system