podcast

Generate two-host podcast videos from URLs or topic briefs.

38|7|Updated May 1, 2026
One-click install
npx skills add https://github.com/Pika-Labs/Pika-Plugins --skill podcast-pika-labs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: podcast
Source: https://github.com/Pika-Labs/Pika-Plugins/tree/main/skills/podcast
Command: npx skills add https://github.com/Pika-Labs/Pika-Plugins --skill podcast-pika-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns a URL or free-form topic into a polished two-host podcast video, removing the need to manually research, script, voice, and render a conversational clip.

Core Features & Use Cases

  • URL review mode: Scrapes a website, extracts concrete facts, and transforms them into a structured podcast episode.
  • Topic mode: Builds an interview, debate, or explainer from a plain-language brief, including persona-aware handling when real public figures are mentioned.
  • End-to-end video generation: Creates host portraits and background assets, resolves voice IDs, renders four sequential acts, and concatenates the final 1-minute video.
  • Use case: Ask for a skeptical podcast review of a product page, a two-scientist debate on a research topic, or an interview-style clip about a startup or public figure.

Quick Start

Ask the podcast skill to make a two-host podcast video about a URL or topic, and it will generate the script, voices, visuals, and final render automatically.

Frequently Asked Questions about podcast

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

FAQPage Schema
How do I turn a website URL into a two-host podcast video?

The Skill scrapes the website URL to extract concrete facts, structures them into a conversational script, and renders the final concatenated video without requiring manual editing.

Can I generate an interview or debate podcast from a free-form topic brief?

Yes, the Skill accepts a plain-language topic brief to build interview, debate, or explainer podcasts, applying persona-aware handling when real public figures are mentioned in the text.

How does automated podcast video generation handle voices and visuals?

Automated podcast video generation resolves specific voice IDs and generates host portrait images, then uses four sequential Kling v3-omni act renders to produce the final concatenated video clip.

Does the generated podcast video include captions?

No, the final concatenated podcast video is rendered without captions, providing a clean visual output suitable for creative communication workflows and short explainer episodes.

What are the limitations of generating a two-host podcast video automatically?

The current implementation restricts output to a 1-minute clip generated across four sequential act renders, meaning it is not suited for creating full-length, long-form podcast episodes.