podcast-maker

Name: podcast-maker
Availability: InStock
Author: zhuganglie

Generate YouTube-ready podcast videos from audio and images using Whisper and FFmpeg.

2|1|Updated Jan 31, 2026

Search Tags:#AI #subtitles #whisper #ffmpeg #podcast #video generation

Ready to run

npx skills add https://github.com/zhuganglie/zhuganglie-skills --skill podcast-maker

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: podcast-maker
Source: https://github.com/zhuganglie/zhuganglie-skills/tree/main/skills/podcast-maker
Command: npx skills add https://github.com/zhuganglie/zhuganglie-skills --skill podcast-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the creation of professional-looking podcast videos from audio and images, eliminating the need for manual video editing and complex software.

Core Features & Use Cases

Semantic Image Timing: AI aligns images with audio content based on VTT cues for precise visual storytelling.
Automated Video Generation: Creates YouTube-ready videos with smooth transitions and embedded subtitles.
Use Case: Turn your podcast audio interviews into engaging YouTube videos by providing audio files, images of speakers or topics, and letting the Skill handle the rest.

Quick Start

Use the podcast-maker skill to create a video from 'my_podcast.mp3' using 'intro.png', 'speaker.jpg', and 'topic.png'.

Frequently Asked Questions about podcast-maker

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

FAQPage Schema

How do I create podcast videos from audio and images automatically?▼

To create podcast videos from audio and images, use this tool to generate YouTube-ready videos with smooth transitions. It aligns images with audio content using VTT cues for precise visual storytelling.

How does semantic image timing work for video generation?▼

Semantic image timing works by using local Whisper to generate VTT cues from audio. These cues trigger AI-driven image alignment, matching visuals to the spoken content for automated video generation.

Do I need Whisper and FFmpeg installed to generate YouTube-ready videos?▼

Yes, you need Whisper and FFmpeg installed to generate YouTube-ready videos. These local dependencies handle audio transcription to VTT format and video generation with embedded subtitles and transitions.

What is the best way to align images with podcast audio cues?▼

The best way to align images with podcast audio is using the cue-based workflow. This recommended approach matches images to VTT subtitle cues for precise alignment, while a segment-based workflow offers quick generation.

Can I embed soft subtitles in MP3 podcasts using FFmpeg?▼

Yes, you can embed soft subtitles in MP3 podcasts using FFmpeg. The tool processes audio through Whisper to create VTT cues, then uses FFmpeg to add smooth fade transitions and soft subtitles to the video.

Why use cue-based workflows instead of segment-based for podcast videos?▼

Cue-based workflows provide precise alignment by matching images to individual VTT cues. Segment-based workflows offer quick generation by grouping content, making cue-based better for detailed visual storytelling.