Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

ElevenLabs Text-to-Speech & Podcast

Turns documents and text into narrated audio or a two-host podcast using the ElevenLabs TTS API.

Image & VideoIntermediate★ 432⑂ 48AI score 9/10Last updated: Sep 10, 2026

What it does

  • Converts text and documents (PDF, DOCX, Markdown, plain text) into high-quality MP3 audio via the ElevenLabs TTS API.
  • Single-voice narration: automatically extracts text, chunks it at sentence boundaries (~4000 chars), keeps voice continuity across chunks, and concatenates with ffmpeg.
  • Podcast mode: extracts the source document, has Claude write a natural two-host conversation script as JSON, then renders it with two contrasting voices into one episode.
  • A voices command lists available voices and their IDs so you can pick before generating.

Who it's for

  • Anyone who wants to listen to reports, papers, or long articles on the go
  • Content teams publishing audio versions of docs and newsletters
  • Builders who want a local, NotebookLM-style AI podcast pipeline
  • Users who already have an ElevenLabs account and API key

Examples

  1. "Narrate this PDF report" → text extraction → chunked TTS → ~/Downloads/narration.mp3
  2. "Make a two-host podcast from this document" → auto-written script → dual-voice synthesis → single MP3
  3. "Show me the voices I can use" → voices --json, then choose a deep/bright voice pair for the podcast

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/sanjay3290/ai-skills/HEAD/skills/elevenlabs/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/elevenlabs folder from the GitHub repo sanjay3290/ai-skills into my ~/.claude/skills/elevenlabs/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/sanjay3290/ai-skills.git && mkdir -p ~/.claude/skills && cp -r ai-skills/skills/elevenlabs ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/sanjay3290/ai-skills.git
  2. Copy the skill into Claude's skills folder: mkdir -p ~/.claude/skills && cp -r ai-skills/skills/elevenlabs ~/.claude/skills/
  3. Create an ElevenLabs account and generate an API key.
  4. Export the key: export ELEVENLABS_API_KEY=your_key (or put api_key in the skill's config.json).
  5. Install Python dependencies: pip install PyPDF2 python-docx (needed for PDF/DOCX input).
  6. Install ffmpeg: brew install ffmpeg on macOS, sudo apt install ffmpeg on Ubuntu.
  7. Restart Claude Code and ask something like "turn this document into a podcast" to trigger the skill.
View source on GitHub ↗License: Apache-2.0