skills.rest
corbintalbert9744-art
corbintalbert9744-artCOMMUNITY
Explore all skills by this author →
GitHub

podcast-generator

Convert research and articles into speaker-tagged podcast scripts and MP3 audio.

Updated Feb 9, 2026
Search Tags:#podcast#elevenlabs#tts#chunking#script-writing#audio-production#loudness-normalization
One-click install
npx skills add https://github.com/corbintalbert9744-art/SeraphimTweaks --skill podcast-generator-corbintalbert9744-art
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-generator
Source: https://github.com/corbintalbert9744-art/SeraphimTweaks/tree/main/secondary_skills/podcast-generator
Command: npx skills add https://github.com/corbintalbert9744-art/SeraphimTweaks --skill podcast-generator-corbintalbert9744-art

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert research, articles, or topic notes into ready-to-publish podcast scripts and narrated audio without manual script formatting, chunking for TTS, or audio normalization work.

Core Features & Use Cases

  • Structured Script Generation: Produces ear-friendly, speaker-tagged scripts for solo, duo, interview, debate, or narrative formats with cold opens, segments, takeaways, and outros.
  • TTS Integration: Guidance and example code for rendering lines to ElevenLabs voices with chunking and voice settings to preserve prosody and consistency.
  • Production Prep: Instructions for sentence-boundary chunking, MP3 concatenation, and LUFS loudness normalization using ffmpeg-normalize so episodes meet platform loudness standards.
  • Use Case: Turn a research paper or article into a 15-minute conversational episode with two distinct voices, export MP3, and normalize to -16 LUFS for Spotify/Apple.

Quick Start

Generate a conversational two-host podcast script from the provided article and render MP3 audio using ElevenLabs with loudness normalization to -16 LUFS.

Frequently Asked Questions about podcast-generator

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

FAQPage Schema
How do I turn a research article into a podcast audio file?▼

You can convert research into podcast audio by generating a structured speaker-tagged script from the text, rendering speech via ElevenLabs TTS, and exporting normalized MP3 audio using ffmpeg-normalize.

Can I create a conversational two-host podcast script from written research?▼

Yes, you can generate conversational duo scripts with two distinct voices. The process creates speaker-tagged scripts containing cold opens, segments, takeaways, and outros from your provided research or articles.

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

Yes, ElevenLabs API access is required for text-to-speech rendering. The process uses ElevenLabs voices and sentence-boundary chunking to preserve prosody and consistency across the generated podcast audio.

How do I normalize podcast audio loudness for Spotify and Apple?▼

You normalize podcast audio loudness using ffmpeg-normalize to process concatenated MP3 files to -16 LUFS. This ensures episodes meet standard platform loudness requirements for Spotify and Apple.

Why does text-to-speech chunking matter for podcast production?▼

Text-to-speech chunking at sentence boundaries preserves prosody and consistency in podcast production. It prevents unnatural pauses and maintains voice quality when rendering long scripts through TTS APIs.

What podcast formats can I generate scripts for?▼

You can generate scripts for solo explainers, conversational duos, interviews, debates, and narrative episodes. Each format includes structured elements like cold opens, segments, takeaways, and outros for production readiness.

Related Skills

Explore More Content & Communication Skills→
FlyFireFFlyFireF

ascii-video

Convert video, audio, and text inputs into ASCII art video outputs.

Community
Advanced
mindmorassmindmorass
2

podcast-production

Automate podcast production from recording to RSS distribution with FFmpeg and Whisper.

Community
Advanced
TheArchitectitTheArchitectit
3

audio-gen

Unify text-to-speech, transcription, audio conversion, and editing workflows.

Community
Intermediate
xg-gh-25xg-gh-25
36

podcast-gen

Convert text content into two-host podcast scripts and optional audio via TTS backends.

Community
Advanced