podcast-generation

Name: podcast-generation
Availability: InStock
Author: easyspace-ai

Convert text content into two-host podcast scripts and synthesized audio.

Updated Apr 7, 2026

Search Tags:#workflow #text-to-speech #audio #podcast #script #tts #multivoice

Ready to run

npx skills add https://github.com/easyspace-ai/minote --skill podcast-generation-easyspace-ai

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

Converts text content into podcast-ready scripts and synthesized audio, enabling rapid creation of professional podcasts from written material.

Core Features & Use Cases

Converts articles, reports, or documentation into a two-host podcast format with natural dialogue.
Generates a structured JSON script and synthesizes audio via text-to-speech.
Produces an optional transcript for accessibility and post-production.
Supports English and Chinese content and end-to-end podcast workflow from script to final MP3.

Quick Start

Provide the source text and language, and request a complete podcast audio file with optional transcript.

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 articles into a natural two-host podcast?▼

You can convert text articles into a natural two-host podcast by providing source text and language to generate a structured JSON script and synthesize multi-voice audio via text-to-speech. This orchestrates the end-to-end workflow from script to final MP3.

Does the text-to-speech workflow support English and Chinese podcast generation?▼

Yes, the text-to-speech workflow supports English and Chinese podcast generation. You provide the source text and language to generate a structured JSON script and synthesize multi-voice audio in either language.

How does multi-voice TTS generation work for podcast scripts?▼

Multi-voice TTS generation works by converting your source text into a structured JSON script formatted as natural dialogue, then synthesizing the audio with distinct voices for each host. This creates a two-host podcast MP3 from your written material.

Do I need to provide a script or just raw text to generate podcast audio?▼

You only need to provide raw text and specify the language to generate podcast audio. The workflow automatically creates the structured JSON script and synthesizes the multi-voice TTS audio for you.

What limitations should I expect when converting reports to podcast audio?▼

When converting reports to podcast audio, you should expect the workflow to require the requests dependency and process content strictly in English or Chinese. The output is a structured JSON script, synthesized multi-voice TTS audio, and an optional transcript.