skills.rest
kyirexy
kyirexyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

podcast-generation

Generate two-host conversational podcasts as MP3 and Markdown transcript.

Updated Mar 5, 2026
Search Tags:#text-to-speech#content creation#scripting#podcast#audio generation#tts
One-click install
npx skills add https://github.com/kyirexy/dearclaw --skill podcast-generation-kyirexy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-generation
Source: https://github.com/kyirexy/dearclaw/tree/main/skills/public/podcast-generation
Command: npx skills add https://github.com/kyirexy/dearclaw --skill podcast-generation-kyirexy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill automates the creation of podcasts from written content, transforming articles, reports, or any text into natural-sounding audio with two hosts.

Core Features & Use Cases

  • Converts text into a two-host conversational podcast script.
  • Synthesizes natural male and female voices using text-to-speech.
  • Generates an MP3 audio file and a Markdown transcript.
  • Supports both English and Chinese content.
  • Use Case: Quickly create an audio version of a blog post or a technical document for easy consumption on the go.

Quick Start

Use the podcast-generation skill to create a podcast from the provided article text, saving the output to /mnt/user-data/outputs/my-podcast.mp3.

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 podcast audio file?▼

To convert text to a podcast, this skill generates a structured two-host conversational script from your input and synthesizes speech using text-to-speech, outputting an MP3 audio file alongside a Markdown transcript.

Does text-to-speech podcast generation support Chinese content?▼

Yes, text-to-speech podcast generation supports both English and Chinese content, creating structured two-host conversational scripts with natural male and female voices for either language.

Do I need a specific TTS API to generate a two-host podcast?▼

Yes, generating a two-host podcast requires Volcengine TTS API credentials. The skill relies on this specific text-to-speech service to synthesize male and female voices for audio generation.

What is the best way to turn a blog post into audio?▼

The best way to turn a blog post into audio is using automated script generation to create a two-host dialogue, which is then synthesized into a natural-sounding MP3 file for easy consumption.

What output formats do I get from automated podcast scripting?▼

Automated podcast scripting produces an MP3 audio file containing the synthesized two-host conversation and a Markdown transcript of the generated dialogue for your text records.

Related Skills

Explore More Content & Communication Skills→
gman-roboticsgman-robotics

podcast-generation

Generates MP3 podcast audio and markdown transcripts from text using Volcengine TTS API.

Official
Intermediate
Citrus-bitCitrus-bit
135

podcast-generation

Generate two-host podcast MP3s from text with optional transcripts.

Community
Intermediate
KaiserWhoLearnsKaiserWhoLearns

gtts

Convert long text into a single MP3 audio file using Google's gTTS.

Community
Intermediate
sanjay3290sanjay3290
392

elevenlabs

Convert text and documents into audio using the ElevenLabs text-to-speech API.

Community
Intermediate