elevenlabs-tts

Generate audio from text using the ElevenLabs API with configurable voices.

3|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/pinion05/skills --skill elevenlabs-tts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: elevenlabs-tts
Source: https://github.com/pinion05/skills/tree/main/elevenlabs-tts
Command: npx skills add https://github.com/pinion05/skills --skill elevenlabs-tts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires elevenlabs, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill enables developers and content creators to produce high-quality audio from text using ElevenLabs' API, eliminating manual voice recording and reducing turnaround time for voice-enabled content.

Core Features & Use Cases

  • Voice presets: Select from multiple preconfigured voices (rachel, adam, bella, elli, josh, arnold, ava) for quick, consistent output.
  • Parameter control: Tune stability and similarity_boost to balance expressiveness and fidelity.
  • Flexible integration: Use via Python API or CLI to automate narration, accessibility features, or podcast generation.
  • Output management: Automatically creates output directories and saves audio files to a specified path.
  • Use cases: generate narration for videos, accessibility narration for articles, or on-demand voice responses in chatbots.

Quick Start

  • Ensure ELEVENLABS_API_KEY is set (in .env or environment).
  • Run python scripts/elevenlabs_tts.py "Your text here" to generate audio with the default voice.
  • Use --voice, --output, --stability, and --similarity to customize voice, output, and settings.
  • List available voices with python scripts/elevenlabs_tts.py "" --list-voices

Frequently Asked Questions about elevenlabs-tts

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

FAQPage Schema
How do I generate text-to-speech audio using the ElevenLabs API in Python?

You can generate text-to-speech audio by running the included Python script with your text, which utilizes the ElevenLabs API to convert the input string into natural-sounding speech audio files.

Can I automate voice generation for narration from the command line?

Yes, you can automate voice generation from the command line by executing the Python script with text arguments and optional flags to specify the output path and voice parameters for automated narration workflows.

What preset voices are available for text-to-speech generation?

The text-to-speech generation supports multiple preset voices including rachel, adam, bella, elli, josh, arnold, and ava, which you can list directly via the command line interface.

Do I need an API key to convert text into speech with this tool?

Yes, you must set the ELEVENLABS_API_KEY in your environment or a .env file, alongside installing the required Python dependencies, to successfully authenticate and generate speech audio.

How do I control voice expressiveness when converting text to speech?

You can control voice expressiveness during text-to-speech conversion by tuning the stability and similarity_boost parameters via command line flags to balance fidelity and expressiveness.

What is the best way to manage audio output files when generating speech?

The tool automatically creates output directories and saves the generated speech audio files to a specified path, which you can define using the output flag during command line execution.