skills.rest
e2662020
e2662020COMMUNITY
Explore all skills by this author →
GitHub

Podcast Generate

Generate podcast scripts and WAV audio from text or web research.

1|Updated May 1, 2026
Search Tags:#script generation#llm#web search#content repurposing#podcast#audio synthesis#tts
One-click install
npx skills add https://github.com/e2662020/QuickMovie --skill podcast-generate-e2662020
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Podcast Generate
Source: https://github.com/e2662020/QuickMovie/tree/main/skills/podcast-generate
Command: npx skills add https://github.com/e2662020/QuickMovie --skill podcast-generate-e2662020

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk.

What problem does it solve?

This Skill eliminates the tedious manual work of creating podcast episodes, including writing natural conversational scripts, recording audio, and editing final files, letting you turn raw text content or web research into a complete, publishable podcast in minutes.

Core Features & Use Cases

  • Dual and Single-Host Podcast Generation: Create natural-sounding conversational podcasts with two hosts or single-host narrative episodes, with customizable host names, voices, and speaking speeds.
  • Flexible Input Support: Use uploaded text files (txt, md, pdf, docx, etc.) or let the Skill search the web for information on any user-specified topic as source material.
  • Automatic Duration and Structure Adjustment: Scripts are automatically scaled to 3-20 minutes based on content length, with built-in narrative structure (opening, multi-dimensional main content, actionable summary) and natural conversational flow.
  • Use Case Example: If you have a 15-page industry analysis report, use this Skill to automatically convert it into a 12-minute dual-host podcast discussing key insights, ready to publish without any recording or editing work.

Quick Start

Provide the Skill with either a text file of your content or a topic to research, along with your desired output directory, and it will automatically generate both an editable Markdown podcast script and a complete WAV audio file for you.

Frequently Asked Questions about Podcast Generate

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

FAQPage Schema
How do I convert a text file into a podcast audio file automatically?▼

To convert a text file into a podcast audio file, you provide documents like txt, md, or pdf to the Skill. It uses LLM-based script generation and TTS audio synthesis to output a Markdown script and a WAV audio file automatically.

Can I generate a dual-host conversational podcast from web search results?▼

Yes, you can generate a dual-host conversational podcast from web search results. The Skill takes a user-specified topic, searches the web for information, and creates a natural-sounding dual-host or single-host audio episode.

How does automatic podcast duration scaling work for content repurposing?▼

Automatic podcast duration scaling works by adjusting the generated script length based on the input content size. The audio output scales naturally between 3 and 20 minutes, ensuring the podcast accurately reflects the source material's depth.

What audio formats and TTS parameters can I customize for podcast generation?▼

For podcast generation, the TTS audio synthesis outputs WAV audio files. You can customize voice selection, speaking speeds, and pause parameters to control the pacing and delivery of the final audio output.

Do I need audio editing software to produce a podcast from an industry report?▼

No, you do not need audio editing software to produce a podcast from an industry report. The Skill eliminates manual recording and editing, directly outputting a publishable WAV file and an editable Markdown script.

What is the best way to create a podcast script using LLM and TTS?▼

The best way to create a podcast script using LLM and TTS is providing raw text or a topic to this Skill. It applies validation and retry logic for script generation and synthesizes speech, outputting both Markdown and WAV files.

Related Skills

Explore More Content & Communication Skills→
Imad-OuteImad-Oute
2

mh-mgi-knowledge-curator

Convert MD, PDF, and text sources into indexed mental models via a 4-step workflow.

Community
Advanced
pavan53732pavan53732

Podcast Generate

Generate podcast scripts and WAV audio from text or web search results.

Community
Intermediate
EnztunEnztun

Podcast Generate

Generate podcast scripts and audio from text files or web search results.

Community
Intermediate
LogicPyLogicPy
8

Podcast Generate

Generate podcast episodes from text or web search results.

Community
Intermediate