podcast

Generates a 60-second two-host podcast video from a URL or free-form topic using Kling v3-omni.

1|Updated Jun 20, 2026
One-click install
npx skills add https://github.com/BeanyZoldyck/moggie --skill podcast-beanyzoldyck
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: podcast
Source: https://github.com/BeanyZoldyck/moggie/tree/main/.agents/skills/podcast
Command: npx skills add https://github.com/BeanyZoldyck/moggie --skill podcast-beanyzoldyck

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating a two-host podcast-style video normally requires scripting, voice recording, filming, and editing; this Skill automates the entire pipeline from a single URL or topic into a finished 1-minute dialogue video. ## Core Features & Use Cases - URL and Topic Modes: Accepts a website, GitHub repo, or article URL (scraped for factual anchors) or a free-form brief with custom hosts, angles, and personas. - Four-Act Scripted Dialogue: Writes a Hook → Deep-dive → Pivot → Verdict script with jokes, interruptions, and a skeptic-flip moment, then renders four sequential 15-second Kling v3-omni acts with native two-voice audio. - Voice and Likeness Controls: Supports Kling preset voices, optional user voice cloning for Host A, custom host/background images, and archetype portraits instead of deepfakes for named public figures. - Use Case: Ask for a podcast review of a product launch page and receive a concatenated video URL of two hosts debating its features in about 8-18 minutes. ## Quick Start Ask the assistant to make a podcast about a specific URL or topic, for example: make a podcast reviewing https://pika.art with a skeptical second host.

Frequently Asked Questions about podcast

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

FAQPage Schema
How do I make a two-host podcast video from a URL?

Provide any website, GitHub repo, or article URL as the input. The skill captures the page, extracts product facts and a jokeable detail, writes a four-act dialogue script, and renders four 15-second Kling v3-omni acts that are concatenated into one video URL.

Can I create a podcast video about a topic without a URL?

Yes, free-form topic mode accepts any brief such as a debate, interview, or explainer. It parses the subject, hosts, and angle from your text, then anchors the script in clearly framed observations rather than invented facts.

Can I use my own voice or a celebrity likeness in the podcast?

Your own voice can be cloned for Host A via the use_avatar option. Named public figures are rendered as archetype portraits by default rather than photographic likenesses, unless you explicitly supply your own host image.

Why are captions not added to the podcast video?

Captions are skipped because Whisper auto-transcription is unreliable on podcast dialogue containing product names, persona names, and technical jargon. The native Kling Omni audio track is the intended deliverable.

How long does podcast video generation take?

Typical wall-clock time is 8 to 18 minutes. Asset generation takes 30-90 seconds, scripting 1-3 minutes, the four sequential Kling acts 6-14 minutes, and final concatenation under 90 seconds.