Podcast Generate

Generate podcast scripts and WAV audio from text or web-searched topics.

Updated Jun 1, 2026
One-click install
npx skills add https://github.com/atro2829-hub/APPLE-NET-NEW --skill podcast-generate-atro2829-hub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Podcast Generate
Source: https://github.com/atro2829-hub/APPLE-NET-NEW/tree/main/skills/podcast-generate
Command: npx skills add https://github.com/atro2829-hub/APPLE-NET-NEW --skill podcast-generate-atro2829-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill turns long-form material or a web topic into a ready-to-listen podcast, so users can quickly convert reading material into a spoken format for review, sharing, or learning.

Core Features & Use Cases

  • File-to-podcast generation: Takes text-based source material and produces a dual-host or single-host podcast script plus WAV audio.
  • Topic-based podcast generation: Searches the web for a user-specified topic, compiles source material, and generates a narrated episode.
  • Controlled delivery: Adapts episode length, speaker roles, voice selection, speed, and pause timing while validating script structure and retrying failed generations.
  • Use Case: A user uploads a report and gets a conversational podcast version for commutes, or asks for a current-events topic and receives a synthesized episode based on live search results.

Quick Start

Use the Podcast Generate skill to turn the attached article or your chosen topic into a podcast script and WAV audio in the 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 turn text into a podcast audio file?

To turn text into a podcast, this Skill generates a spoken script and synthesizes TTS audio. It converts uploaded text-based material into a dual-host or single-host podcast script and outputs a stitched WAV audio file.

Can I generate podcast audio from a web-searched topic?

Yes, you can generate podcast audio from a web-searched topic. The Skill searches the web for your specified topic, compiles source material, and generates a narrated podcast episode based on the live search results.

How do I control podcast duration and speaker voices in TTS synthesis?

You control podcast duration and TTS synthesis by configuring voice selection, speed, and pause timing. The Skill adapts episode length and speaker roles while validating the script structure before generating the final audio.

Do I need the z-ai-web-dev-sdk to generate spoken content?

Yes, you need the z-ai-web-dev-sdk dependency to generate spoken content. The Skill relies on this SDK to perform LLM script generation, TTS synthesis, and WAV segment stitching for your podcast output.

What is the best way to summarize current events into spoken content?

The best way to summarize current events into spoken content is using a topic-based podcast generator. This Skill compiles live web search results into a structured script and synthesizes a current-events briefing in WAV audio format.

Why does podcast script generation fail or produce incomplete audio?

Podcast script generation may fail due to invalid script structure or TTS synthesis errors. The Skill applies script validation and automatically retries failed generations to ensure complete WAV segment stitching.