podcast-generation

Transforms text content into conversational two-host podcast audio MP3s using Python scripts and TTS APIs.

Updated Aug 23, 2026

Search Tags:#text-to-speech #audio generation #podcast creation #conversational dialogue #document-to-podcast

Ready to run

npx skills add https://github.com/ainlper/dra-drb2 --skill podcast-generation-ainlper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: podcast-generation
Source: https://github.com/ainlper/dra-drb2/tree/main/deer-flow/skills/public/podcast-generation
Command: npx skills add https://github.com/ainlper/dra-drb2 --skill podcast-generation-ainlper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires volcengine, minimax, requests, json, uuid, concurrent.futures, os, re, argparse, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of converting written content into professional-quality podcast audio featuring two hosts, eliminating the need for complex audio editing and synthesis.

Core Features & Use Cases

Text to Podcast Conversion: Convert articles, reports, and other written content into structured JSON scripts for two-host podcasts.
Text-to-Speech Synthesis: Use text-to-speech technology to generate realistic host voices.
Use Case: Easily turn a long report into an engaging podcast that can be consumed in audio format.

Quick Start

Generate a podcast from the article 'AI and Its Future' using the 'podcast-generation' skill.

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 to a conversational podcast audio?▼

To convert text to a conversational podcast, this Skill transforms written content into structured JSON scripts for two-host dialogue, synthesizes realistic voices using text-to-speech APIs, and mixes the audio into a final MP3 file.

Can I generate a two-host podcast from a long document without audio editing?▼

Yes, you can generate a two-host podcast from a long document without audio editing. The process automatically structures the text into a conversational dialogue script and synthesizes the audio, eliminating the need for complex manual mixing.

Do I need external text-to-speech APIs to generate podcast audio?▼

Yes, you need external text-to-speech APIs to generate podcast audio. This Skill relies on external TTS providers like volcengine and minimax to synthesize realistic host voices and handle the audio generation process.

What is the best way to turn an article into an MP3 podcast dialogue?▼

The best way to turn an article into an MP3 podcast dialogue is using a Python-based text-to-podcast conversion process. It parses the document into a conversational JSON script, synthesizes speech, and mixes the tracks into an MP3 file.

Does podcast generation work with Python scripts for audio mixing?▼

Yes, podcast generation works with Python scripts for audio mixing. The implementation uses Python modules like concurrent.futures and uuid to manage concurrent text-to-speech synthesis and mix the resulting audio tracks into MP3 files.

Why use a structured JSON script for text-to-speech podcast creation?▼

Using a structured JSON script for text-to-speech podcast creation separates the conversational dialogue logic from the audio synthesis. This structured approach ensures the two-host dialogue is accurately mapped before generating the final MP3 file.