podcast-generation

Convert text content into a two-host podcast script and synthesize MP3 audio.

2|1|Updated May 11, 2026

Search Tags:#text-to-speech #audio synthesis #audio editing #content conversion #podcast generation

Ready to run

npx skills add https://github.com/LittleSongxx/SoulSearcher --skill podcast-generation-littlesongxx

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: podcast-generation
Source: https://github.com/LittleSongxx/SoulSearcher/tree/main/skills/public/podcast-generation
Command: npx skills add https://github.com/LittleSongxx/SoulSearcher --skill podcast-generation-littlesongxx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill converts written content into conversational two-host podcast audio format, saving you time and effort in creating audio content.

Core Features & Use Cases

Text to Podcast Script: Converts any text content into a structured JSON script for two-host conversational dialogue.
Text-to-Speech Synthesis: Generates natural-sounding audio for male and female hosts using text-to-speech technology.
Audio Mixing: Combines audio chunks into a final podcast MP3 file.
Multi-Language Support: Works with both English and Chinese content.

Quick Start

Generate a podcast from the text file 'interview.md'.

Frequently Asked Questions about podcast-generation

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

FAQPage Schema

How do I convert text content into a podcast audio file?▼

Convert text content into a podcast audio file by transforming it into a structured two-host conversational script and synthesizing natural-sounding dialogue using text-to-speech, outputting a final MP3. It processes text inputs like markdown files to generate the audio.

Can I generate Chinese text-to-speech audio or does it only work in English?▼

You can generate Chinese text-to-speech audio as well as English. The podcast generation process supports both languages, converting text content into structured JSON scripts and synthesizing natural-sounding two-host conversational dialogue for either language.

How does two-host conversational dialogue generation work for podcasts?▼

Two-host conversational dialogue generation works by converting written text content into a structured JSON script featuring male and female hosts, then using text-to-speech synthesis to generate natural-sounding audio chunks that are mixed into a final podcast MP3.

What is the best way to automate podcast generation from markdown files?▼

The best way to automate podcast generation from markdown files is using a tool that converts the text into a structured JSON script and synthesizes it with text-to-speech. This process automatically generates and mixes male and female host audio chunks into a final podcast MP3.

Does text-to-speech podcast synthesis require any external audio editing dependencies?▼

No external audio editing dependencies are required for text-to-speech podcast synthesis. The process handles audio mixing internally, combining individual synthesized audio chunks into a final podcast MP3 file without needing additional tools.