podcast-video

Merge PPTX slides, audio, and JSON scripts into MP4 videos.

45|11|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/beyonai/ByClaw --skill podcast-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: podcast-video
Source: https://github.com/beyonai/ByClaw/tree/main/middleware/openclaw/skills/podcast-video
Command: npx skills add https://github.com/beyonai/ByClaw --skill podcast-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, libreoffice, pymupdf, and includes scripts (resource) components.

What problem does it solve?

This skill solves the complex, multi-step challenge of synchronizing audio, slide decks, and subtitles into a final, high-quality video, eliminating manual editing bottlenecks.

Core Features & Use Cases

  • Automated Synthesis: Combines PPTX slides, audio files, and JSON scripts into a polished 1080p MP4 video.
  • Precise Synchronization: Uses sentence-level timestamps and slide annotations to ensure perfect alignment between visuals, audio, and burned-in subtitles.
  • Use Case: A content creator can take a finished podcast audio and a slide deck and use this skill to generate a ready-to-publish video with perfectly timed subtitles and slide transitions in minutes.

Quick Start

Use the podcast-video skill to synthesize the podcast project located in the current directory into a final video file.

Frequently Asked Questions about podcast-video

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

FAQPage Schema
How do I convert PPTX slides and audio into a single MP4 video?

To convert PPTX slides and audio into an MP4 video, this skill merges slide frames and audio tracks using ffmpeg. It renders the slides via LibreOffice and PyMuPDF, then encodes them into a synchronized 1080p video file.

How do I burn subtitles into a podcast video with precise slide transitions?

Burning subtitles into a podcast video relies on JSON-based scripts and sentence-level timestamps. The skill aligns slide transitions and subtitle text exactly to your TTS audio metadata before encoding the final MP4.

Do I need LibreOffice and ffmpeg installed to automate podcast video production?

Yes, you need LibreOffice and ffmpeg installed to automate podcast video production. These dependencies, along with PyMuPDF, handle the slide rendering, multimedia synthesis, and video encoding operations required by the skill.

Can I synchronize PPTX slide transitions with TTS audio timestamps automatically?

You can synchronize PPTX slide transitions with TTS audio timestamps automatically by providing a JSON script. The skill uses your sentence-level timing metadata to ensure perfect alignment between visuals and audio playback.

What is the best way to automate merging a slide deck and podcast audio into a video?

The best way to automate merging a slide deck and podcast audio into a video is using a script-driven synthesis tool. This skill combines PPTX frames, audio tracks, and JSON metadata to eliminate manual editing bottlenecks.

Why does podcast video synthesis require PyMuPDF for processing slide decks?

Podcast video synthesis requires PyMuPDF to process slide decks because it handles the rendering of PPTX slide frames into images. These frames are then merged with audio and subtitles by ffmpeg to create the final MP4.