video-podcast-maker
An automated 4K video podcast creation tool supporting multiple platforms and languages.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.4k
- Source
- skill-github
Overview
Video Podcast Maker is an automated tool for generating professional video podcasts, supporting platforms such as Bilibili, YouTube, Xiaohongshu, Douyin, and WeChat Video Channel. It combines research, script generation, multi-engine TTS (Edge/Azure/Doubao/CosyVoice), Remotion video rendering, and FFmpeg audio mixing. Compatible with any coding agent that supports SKILL.md, such as Claude Code, OpenClaw, etc. Users simply describe the topic in natural language, and the coding agent guides them through each step; users make creative decisions while technical details are handled by the agent.
Capabilities
- ▪Web search and content collection
- ▪Structured narrative script generation
- ▪Multi-engine TTS support
- ▪Video composition and animation based on React
- ▪Real-time preview and debugging
- ▪Automatic audio-video synchronization
Use cases
Setup
Please refer to the installation steps in the README, and install using npm or yarn.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which platforms are supported?
Supports Bilibili, YouTube, Xiaohongshu, Douyin, and WeChat Video Channel.
What dependencies are required?
Requires Node environment and relevant API keys.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.