Does this skill support multi-voice podcasts?

Yes, it features a specialized podcast mode that generates a conversational script and uses two different voices for a natural discussion format.

How does it handle very long documents?

It automatically splits long text into chunks at sentence boundaries (~4000 characters) to comply with API limits and then merges them into a single seamless audio file.

What file formats are supported for conversion?

The skill can extract and process text from PDF, DOCX, Markdown, and plain text files for audio conversion.

Is ffmpeg required to run this skill?

Yes, ffmpeg must be installed on your system to enable the concatenation of audio chunks and the generation of multi-voice podcasts.

Do I need an ElevenLabs account to use this?

Yes, you require an ElevenLabs API key which can be provided in the skill's config.json file or set as an environment variable.

ElevenLabs Audio & Podcast Generator

Name: ElevenLabs Audio & Podcast Generator
Author: sanjay3290

bysanjay3290

•

140

•

コンテンツ管理

Transforms text and documents into professional-grade audio narrations and multi-host podcasts using ElevenLabs AI.

This skill integrates ElevenLabs' high-fidelity text-to-speech technology directly into Claude's workflow, allowing users to instantly convert documents, scripts, or plain text into natural-sounding audio. It uniquely features a podcast mode that can automatically generate a conversational script for two AI hosts based on source documents, manage text chunking for long-form content, and handle the technical assembly of the final audio file. It is an essential tool for content creators and developers looking to repurpose written material into accessible, engaging audio formats without leaving their development environment.

主な機能

01Automated audio concatenation using ffmpeg for production-ready outputs

02Intelligent text chunking and sentence boundary detection for seamless audio

03Integrated voice discovery and management via ElevenLabs API

04140 GitHub stars

05High-quality single-voice narration for PDF, DOCX, and Markdown files

06Automated multi-host podcast generation from static documents

ユースケース

01Creating audio versions of tutorials and scripts directly from the terminal

02Generating high-quality narrations of long-form PDFs or research papers for hands-free consumption

03Converting technical documentation or blog posts into engaging, two-person podcast discussions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sanjay3290/ai-skills elevenlabs

For use in Claude.ai and ChatGPT

Download Skill