podcast-generator

Generate podcast scripts and audio episodes using ElevenLabs text-to-speech.

Updated May 17, 2026
One-click install
npx skills add https://github.com/Amna-exe/EventFlow_App --skill podcast-generator-amna-exe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: podcast-generator
Source: https://github.com/Amna-exe/EventFlow_App/tree/main/Final-MAD-project-main-4zipzipzipzipzip-1-ite1zipzip/.local/secondary_skills/podcast-generator
Command: npx skills add https://github.com/Amna-exe/EventFlow_App --skill podcast-generator-amna-exe

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Turning research, articles, or topics into polished podcast episodes requires scripting, voice production, and audio engineering skills that most creators lack. This Skill automates the full pipeline from structured research to conversational scripts and normalized audio files. ## Core Features & Use Cases - Script Generation: Produces podcast scripts in multiple formats (solo explainer, conversational duo, interview, debate, narrative) with segment timing and speaker balance guidelines. - Audio Production: Renders scripts to audio via ElevenLabs TTS with per-speaker voices, then normalizes loudness to the -16 LUFS podcast standard using ffmpeg. - Series Planning: Creates show bibles, episode calendars, and continuity conventions for recurring podcasts, plus multilingual episode support. - Use Case: A user says "create an episode about this week's Champions League results" and receives a researched two-host script, then a finished MP3 ready for publishing. ## Quick Start Ask the assistant to create a podcast episode about your chosen topic and specify whether you want a script only or full audio production with an ElevenLabs API key.

Frequently Asked Questions about podcast-generator

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

FAQPage Schema
How do I turn an article into a podcast episode?

Provide the article or topic and request a podcast episode. The Skill researches the subject with parallel web searches, writes a conversational script in your chosen format, and optionally renders audio with ElevenLabs voices.

How do I generate podcast audio with ElevenLabs?

Set the ELEVENLABS_API_KEY environment variable, then the Skill renders each script line with a per-speaker voice using the eleven_multilingual_v2 model, concatenates segments with pydub, and normalizes loudness to -16 LUFS via ffmpeg-normalize.

Can I create a podcast script without audio generation?

Yes, script-only mode delivers the full script with production notes including word count, estimated duration, segment breakdown, and voice recommendations. No ElevenLabs API key is required for this mode.

Does ElevenLabs support non-English podcast generation?

Yes, use the eleven_multilingual_v2 model for non-English scripts and search for native voices in the target language. Set stability slightly higher (0.50-0.55) and test voices with a short sample before full rendering.

Why does my generated podcast audio sound inconsistent?

Long single TTS calls cause voice drift and stuttering with eleven_multilingual_v2. Chunk utterances at sentence boundaries under roughly 800 characters and pass previous_text and next_text parameters to preserve prosody across chunks.

What are the limitations of AI podcast generation?

Audio generation requires a paid ElevenLabs API key costing roughly $3-5 per 20-minute episode. Voices may mispronounce technical terms, requiring phonetic spelling in scripts, and non-English voice quality varies by language.