podcast-generator

Generates podcast scripts and multi-speaker audio from research documents.

18|4|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/DevHive1/DevHive-Cli --skill podcast-generator-devhive1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-generator
Source: https://github.com/DevHive1/DevHive-Cli/tree/main/agents/podcast-generator
Command: npx skills add https://github.com/DevHive1/DevHive-Cli --skill podcast-generator-devhive1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires elevenlabs, pydub, ffmpeg-normalize.

What problem does it solve?

This skill eliminates the manual effort required to convert dense research, articles, or complex topics into engaging, high-quality audio content.

Core Features & Use Cases

  • Script Generation: Automatically creates conversational, multi-host podcast scripts based on provided source material using a proven narrative arc.
  • Audio Synthesis: Integrates with ElevenLabs to generate realistic, multi-speaker audio with customizable voice settings and prosody.
  • Post-Processing: Includes automated loudness normalization to meet industry standards for platforms like Apple and Spotify.

Quick Start

Use the podcast-generator skill to turn the research paper in the current directory into a ten-minute conversational podcast episode.

Frequently Asked Questions about podcast-generator

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

FAQPage Schema
How do I convert research documents into a conversational podcast?▼

To convert research documents into a conversational podcast, this skill automatically generates multi-host scripts from source material and synthesizes realistic audio using ElevenLabs. It structures narratives and applies audio normalization for professional-grade output.

Do I need an ElevenLabs API key to generate podcast audio from articles?▼

Yes, you need an ElevenLabs API key to generate podcast audio from articles. The skill requires ElevenLabs integration for realistic multi-speaker voice synthesis and customizable prosody settings.

What's the best way to ensure generated podcast audio meets Spotify loudness standards?▼

The best way to ensure generated podcast audio meets Spotify loudness standards is using automated post-processing. This skill applies ffmpeg-normalize to automatically enforce loudness compliance for platforms like Apple and Spotify.

Can I create multi-speaker audio dynamics from research papers automatically?▼

Yes, you can create multi-speaker audio dynamics from research papers automatically. The skill generates conversational scripts with multi-host dynamics and uses ElevenLabs to synthesize distinct voices for each speaker.

What Python dependencies are required for automated scriptwriting and TTS podcast generation?▼

Required dependencies for automated scriptwriting and TTS podcast generation include the ElevenLabs API for voice synthesis, pydub for audio manipulation, and ffmpeg-normalize for loudness compliance.