text-to-speech

Convert text to natural speech via the ElevenLabs API in Python and JavaScript.

Updated Feb 7, 2026
One-click install
npx skills add https://github.com/Zemelware/Lucid --skill text-to-speech-zemelware
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/Zemelware/Lucid/tree/main/.agents/skills/text-to-speech
Command: npx skills add https://github.com/Zemelware/Lucid --skill text-to-speech-zemelware

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill converts plain text into natural, lifelike speech using ElevenLabs API, enabling quick voiceover generation, narrated content, and multilingual output.

Core Features & Use Cases

  • Voice synthesis: Generate high-quality speech across 70+ languages with multiple models.
  • Voice customization: Adjust tone and speed using per-request voice settings.
  • Use Case: Create voiceovers for videos, podcasts, or interactive narrations with automated text input.

Quick Start

Use the ElevenLabs text-to-speech skill to generate speech from the text "Hello, world" using a valid API key.

Frequently Asked Questions about text-to-speech

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

FAQPage Schema
How do I convert text to speech using ElevenLabs in my code?

To convert text to speech, you call the ElevenLabs API with your text input and an ELEVENLABS_API_KEY. This process generates natural, lifelike speech audio from plain text. It works across Python and JavaScript environments.

Do I need an ElevenLabs API key to generate voiceovers?

Yes, generating voiceovers requires an active ELEVENLABS_API_KEY and internet access to call the API. You must configure this key in your environment before synthesizing speech or customizing voice tone and speed.

Can I use this text-to-speech tool to generate audio in multiple languages?

Yes, this text-to-speech tool supports generating audio in 74+ languages. It uses models like eleven_multilingual_v2 and eleven_v3 to create natural speech for diverse global voiceover and narration needs.

What is the best way to customize voice tone and speed for an audio narration?

The best way to customize voice tone and speed is by applying per-request voice settings during the text-to-speech API call. This allows you to adjust audio output characteristics dynamically for specific narration requirements.

Which ElevenLabs models are available for synthesizing speech?

Available models for synthesizing speech include eleven_v3, eleven_multilingual_v2, and eleven_flash_v2_5. These models provide different performance and language capabilities for generating natural voiceovers from text.