Elevenlabs Tts

This wraps the ElevenLabs API for text-to-speech with seven preset voices (rachel, adam, bella, and others) and sensible defaults so you don't have to look up voice IDs every time. You get direct Python module access or command line usage, with controls for stability and similarity boost if you need to tune expressiveness versus consistency. The script handles directory creation and returns absolute paths, which is thoughtful. It's straightforward integration work: drop your API key in the env file and you're generating audio files. Good for prototyping voice features or batch generating narration without building the API wrapper yourself.

skills.sh installs: 310
GitHub stars: 412
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add glebis/claude-skills --skill elevenlabs-tts --agent claude-code

Installs into .claude/skills of the current project.

Files

ElevenLabs Text-to-Speech

Overview

Generate professional audio files from text using ElevenLabs' advanced text-to-speech API. The skill provides pre-configured voice presets with sensible defaults, voice parameter customization, and direct access to the scripts/elevenlabs_tts.py script for programmatic control.

Quick Start

To generate audio from text:

Ensure the .env file contains a valid ELEVENLABS_API_KEY
Execute the script with text: python scripts/elevenlabs_tts.py "Your text here"
Specify voice and output: python scripts/elevenlabs_tts.py "Text" --voice adam --output audio/output.mp3