video-creator

Automate end-to-end digital-human video creation from script to final render.

27|9|Updated Jan 25, 2026

Search Tags:#tts #remotion #ai-art #video-creation #digital-human #green-screen

Ready to run

npx skills add https://github.com/Leoyishou/personal-ai-company --skill video-creator-leoyishou

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-creator
Source: https://github.com/Leoyishou/personal-ai-company/tree/main/claude-global/skills/video-creator
Command: npx skills add https://github.com/Leoyishou/personal-ai-company --skill video-creator-leoyishou

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, uv, whisper, and includes scripts (resource) components.

What problem does it solve?

创作完整的数字人解说视频需要剧本创作、IP形象设计、语音合成、背景音乐、素材插图与分镜合成等多步环节，本 Skill 将这些环节打通，提供端到端的自动化工作流。

Core Features & Use Cases

自动化剧本生成与确认、IP形象设计、TTS语音合成、背景音乐、数字人视频与 Remotion 合成的完整流程。
适用于社媒短视频、产品解说、技术讲解等场景的竖屏视频创作。
案例：从主题输入到最终成品视频，自动完成 IP 形象、字幕、配乐与剪辑的全链路输出。

Quick Start

Provide a project brief including theme, duration, and language to start the end-to-end video creation.

Frequently Asked Questions about video-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate digital human video creation from a script to final render?▼

Automating digital human video creation requires orchestrating script generation, IP image design, TTS narration, and Remotion composition. This workflow coordinates multi-tool steps to output a complete vertical 9:16 video for social platforms.

Can I generate TTS narration and background music together for a short video?▼

Generating TTS narration and background music together is supported in the video creation workflow. The process synthesizes AI voiceovers and integrates audio tracks with Remotion-based composition to produce the final video output.

Does Remotion support vertical 9:16 video composition for social media platforms?▼

Remotion supports vertical 9:16 video composition for social media platforms. The workflow uses Remotion to composite digital human images, subtitles, and audio tracks into the required aspect ratio for social media distribution.

Do I need ffmpeg and whisper to run the end-to-end video creation workflow?▼

You need ffmpeg, uv, and whisper dependencies to run the end-to-end video creation workflow. These tools handle audio processing, environment management, and speech recognition required for automated script alignment and video rendering.

What is the best way to coordinate AI drawing and TTS steps for digital human videos?▼

The best way to coordinate AI drawing and TTS steps is through Bash-based orchestration. This approach sequences IP image generation, cloud uploads, and voice synthesis to ensure multi-tool workflows execute in the correct order.

Why does automated video composition require Bash-based orchestration?▼

Automated video composition requires Bash-based orchestration to coordinate multi-tool workflows across AI drawing, TTS, and Remotion rendering. This orchestration ensures each step from script generation to final render executes sequentially and reliably.