Podcast Generate

Generate podcast scripts and TTS audio from documents or web sources.

Updated Mar 29, 2026
One-click install
npx skills add https://github.com/Mohabsmar/VoiceDev-2.0 --skill podcast-generate-mohabsmar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Podcast Generate
Source: https://github.com/Mohabsmar/VoiceDev-2.0/tree/main/skills/podcast-generate
Command: npx skills add https://github.com/Mohabsmar/VoiceDev-2.0 --skill podcast-generate-mohabsmar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates turning user-provided content or web search results into ready-to-publish podcast scripts and audio. It saves time by handling scripting, structuring, and TTS audio production in a single workflow.

Core Features & Use Cases

  • From file inputs: convert documents (txt, md, docx, pdf, etc.) into a podcast-ready script and audio.
  • Web search mode: fetches information on a topic and generates a podcast script and audio from the gathered material.
  • Output formats and pacing: automatically adjusts duration (3-20 minutes) and outputs both a Markdown script (podcast_script.md) and a WAV audio file (podcast.wav).
  • Easy integration: uses z-ai-web-dev-sdk to generate the script and synthesize speech, with configurable hosts/guests, voices, and tone.

Quick Start

Provide an input file or a topic and run the generate command to produce podcast_script.md and podcast.wav in your output directory.

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 document into a podcast script and audio?

To convert a document into a podcast, provide an input file like txt, md, docx, or pdf. The Skill processes the content to generate a Markdown script and a WAV audio file automatically.

Can I generate a podcast from a topic using web search results?

Yes, you can generate a podcast from a topic using web search mode. The Skill fetches online information on your specified subject and uses the gathered material to produce a podcast script and audio.

Does podcast generation support dual-host or single-host formats?

Podcast generation supports both dual-host and single-host formats. You can configure the hosts, guests, voices, and tone to structure the dialogue according to your podcast style.

What audio format and duration limits apply to content-to-podcast conversion?

Content-to-podcast conversion outputs a WAV audio file and automatically adjusts the duration from 3 to 20 minutes. It also outputs a Markdown script for your podcast.

Do I need to provide my own text-to-speech tools for automated script generation?

No, you do not need external text-to-speech tools for automated script generation. The Skill uses the integrated z-ai-web-dev-sdk to synthesize speech and generate the podcast audio directly.