podcast-gen

Convert text content into two-host podcast scripts and optional audio via TTS backends.

36|4|Updated Feb 11, 2026

Search Tags:#podcast #tts #script-generation #audio-production #content-automation

Ready to run

npx skills add https://github.com/xg-gh-25/SwarmAI --skill podcast-gen-xg-gh-25

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: podcast-gen
Source: https://github.com/xg-gh-25/SwarmAI/tree/main/backend/skills/s_podcast-gen
Command: npx skills add https://github.com/xg-gh-25/SwarmAI --skill podcast-gen-xg-gh-25

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts text content (articles, reports, documentation) into engaging two-host podcast scripts and synthesized audio, saving time and enabling scalable content production.

Core Features & Use Cases

Automated script generation: turn written content into structured, conversational podcast dialogue for two hosts.
Transcript and audio output: produce human-readable transcripts and optional audio narration via multiple TTS backends.
Flexible backends & fallbacks: supports MCP TTS, OpenAI TTS, Edge TTS, macOS say, with script-only export when no TTS is available.

Quick Start

Provide your source content and let SwarmAI generate a podcast script and audio using available TTS backends.

Frequently Asked Questions about podcast-gen

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

FAQPage Schema

How do I convert text articles into podcast audio?▼

You can automate podcast production from text by generating a structured two-host conversational script from your articles or reports, then synthesizing audio narration using available TTS backends.

What is the best way to automate two-host podcast script generation from reports?▼

Automating two-host podcast script generation involves transforming written reports into structured conversational dialogue, producing human-readable transcripts, and optionally synthesizing audio narration via TTS backends.

Does this podcast text-to-speech tool work with OpenAI TTS and Edge TTS?▼

This podcast text-to-speech tool supports multiple TTS backends including OpenAI TTS, Edge TTS, MCP TTS, and macOS say, with fallback to script-only export when no TTS is available.

Can I generate podcast transcripts without an audio TTS backend?▼

You can generate podcast transcripts without an audio TTS backend by using the script-only fallback mode, which produces human-readable transcripts and structured dialogue even when TTS synthesis is unavailable.

What are the limitations of automated podcast script generation from documentation?▼

Automated podcast script generation from documentation requires source text input and depends on TTS backend availability for audio output, defaulting to script-only transcripts if no TTS service is configured.