speech-generator

Generates speech audio from text using the ElevenLabs Text-to-Speech API.

1|Updated Mar 5, 2026

Search Tags:#audio #elevenlabs #tts #narration #voice generation #speech

Ready to run

npx skills add https://github.com/a0972199950/lazy-cv --skill speech-generator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech-generator
Source: https://github.com/a0972199950/lazy-cv/tree/main/.agents/skills/speech-generator
Command: npx skills add https://github.com/a0972199950/lazy-cv --skill speech-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires dotenv, typescript, ts-node, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill converts written text into natural-sounding speech audio, enabling voice messages, narration, and accessibility features.

Core Features & Use Cases

Text-to-Speech Conversion: Generates high-quality audio from any provided text.
Customizable Voices: Supports ElevenLabs' diverse voice library and custom voice cloning.
Use Case: You need to create an audio version of a blog post for visually impaired users or generate a voiceover for a presentation.

Quick Start

Use the speech-generator skill to convert the text "Hello, this is a test." into an audio file named "output.mp3".

Frequently Asked Questions about speech-generator

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

FAQPage Schema

How do I convert text to speech using the ElevenLabs API?▼

Text to speech conversion is achieved by sending text inputs to the ElevenLabs API to generate natural-sounding audio. You can provide direct text or read from a file to create voice narrations and accessible audio outputs.

Do I need an ElevenLabs API key and voice ID to generate speech audio?▼

Yes, an ElevenLabs API key and a specific voice ID are required prerequisites for operation. These credentials authenticate your requests and determine the exact voice profile used to read your text.

Can I adjust voice stability and similarity boost for ElevenLabs text-to-speech?▼

Yes, you can adjust voice settings including stability, similarity boost, and speed for your text-to-speech generation. These parameters control the vocal consistency and tonal fidelity of the final audio output.

What is the best way to generate an audio narration from a text file?▼

Generating an audio narration from a text file is supported natively by reading the file content directly for text-to-speech processing. This enables you to easily create audio versions of longer documents like blog posts.

Are there limitations when using custom voice cloning for text-to-speech?▼

Limitations depend on your ElevenLabs API tier regarding custom voice cloning availability and usage limits. You must supply the correct custom voice ID in your environment variables to properly route the audio generation request.