video-podcast-maker

Automate 4K video podcast production from topic to MP4 export.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/onelee85/my-skills --skill video-podcast-maker-onelee85
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-podcast-maker
Source: https://github.com/onelee85/my-skills/tree/main/video-podcast-maker
Command: npx skills add https://github.com/onelee85/my-skills --skill video-podcast-maker-onelee85

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires azure-cognitiveservices-speech, dashscope, edge-tts, requests, and includes references (resource) and assets (resource) components.

What problem does it solve?

Converts a topic into a polished, 4K video podcast by automating topic research, script generation, TTS synthesis, video composition with Remotion, and final export, reducing manual setup and production time.

Core Features & Use Cases

  • End-to-end automation from topic to final MP4, including chapter timing, subtitles, and thumbnails.
  • Design-learning and style profiling by extracting design references and applying consistent visuals across videos.
  • Flexible 4K horizontal (16:9) and vertical (9:16) outputs with studio previews and templates.

Quick Start

Describe your topic to Claude Code to start generating a complete 4K video podcast automatically.

Frequently Asked Questions about video-podcast-maker

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

FAQPage Schema
How do I automate video podcast production from a topic to a final MP4?

Automating video podcast production involves using a tool that handles topic research, script generation, TTS synthesis, and Remotion video composition to export a final MP4 automatically.

Can I render 4K video podcasts in both horizontal and vertical formats?

Yes, you can render 4K video podcasts in both 16:9 horizontal and 9:16 vertical formats, complete with synchronized timing, subtitles, and auto-generated thumbnails.

How does TTS synthesis work with Remotion for video podcast generation?

TTS synthesis converts generated scripts into audio, which Remotion then uses to synchronize timing, subtitles, and visual composition for the final video podcast export.

What's the best way to apply consistent visual design across automated video podcasts?

The best way to apply consistent visuals is by using a design-reference library that extracts design profiles and applies them automatically across your video podcast rendering pipeline.

Do I need Azure Cognitive Services and edge-tts to generate video podcast audio?

You need TTS dependencies like Azure Cognitive Services, edge-tts, or Dashscope to synthesize the audio track required for timing synchronization and final video podcast export.

What are the limitations of automating video podcast creation with Remotion?

Limitations include relying on predefined Remotion templates for composition and requiring external TTS services for audio, meaning complex custom animations need manual template adjustments.