skills.rest
huangserva
huangservaCOMMUNITY
Explore all skills by this author →
𝕏@servasyy_aiGitHub

podcast-generator

Generate two-person interview podcast MP3s from Markdown or script text.

155|24|Updated Feb 5, 2026
Search Tags:#automation#markdown#interview#audio#podcast#script#tts
One-click install
npx skills add https://github.com/huangserva/servasyy_skills --skill podcast-generator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-generator
Source: https://github.com/huangserva/servasyy_skills/tree/main/podcast-generator
Command: npx skills add https://github.com/huangserva/servasyy_skills --skill podcast-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires edge-tts, ffmpeg, and includes scripts (resource) components.

What problem does it solve?

从 Markdown 或文本脚本出发，自动生成自然真实的双人访谈播客音频，解放繁琐的逐字编辑与合成工作。

Core Features & Use Cases

  • 双人对话模板：支持晓晓/云扬等角色的对话脚本，自动生成播客结构。
  • 多引擎情感合成：内置 Edge TTS、IndexTTS2、MiniMax 三大引擎，并可按场景调控情感与停顿。
  • 快速起稿与导出：从 Markdown/文本快速生成 MP3，适用于内容创作者、教育、市场宣传等场景。

Quick Start

Run the skill on a Markdown file to produce a podcast.mp3.

Frequently Asked Questions about podcast-generator

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

FAQPage Schema
How do I convert markdown text to a two-person interview podcast?▼

Generating a two-person interview podcast from markdown involves parsing dialogue scripts with emotional cues, synthesizing speech via shared TTS backend engines, and assembling the audio into a final MP3 output.

Can I use edge-tts and ffmpeg to synthesize emotional dialogue audio?▼

Yes, this skill leverages edge-tts for voice synthesis and ffmpeg for audio processing, supporting configurable voices, emotional cues, and pauses to produce natural two-person interview audio.

What is the best way to automate TTS podcast production from scripts?▼

The best way to automate TTS podcast production is using a skill that parses script text, applies emotional cues via multi-engine TTS backends like MiniMax and IndexTTS2, and assembles the final audio automatically into an MP3 file.

Do I need Python runtime and specific TTS engines to generate audio?▼

Yes, you need a Python runtime environment and external TTS engines like edge-tts, IndexTTS2, or MiniMax, plus ffmpeg for audio processing, to execute the shared-lib TTS module and generate podcast audio.

Does this podcast generator support configurable voices and pauses?▼

Yes, the podcast generator supports configurable voices and pauses. It applies emotional cues and adjustable pauses to dialogue scripts, utilizing multiple TTS backends to synthesize natural conversational flow for the final MP3 output.

Related Skills

Explore More Content & Communication Skills→
sgassersgasser
13

podcast

Convert text into podcast-style audio using the browser's Web Speech API.

Community
Basic
Celia-12Celia-12

podcast-generator

Generate podcast scripts and MP3 audio from research articles using ElevenLabs.

Community
Intermediate
MCKRUZMCKRUZ
86

comfyui-voice-pipeline

Automate character voice creation and lip-sync for video production.

Community
Advanced
curiositechcuriositech
181

voice-audio-engineer

Generate speech with ElevenLabs and process audio to broadcast loudness standards.

Official
Advanced