elevenlabs

Generate speech from text using the ElevenLabs API with multiple voices and formats.

Updated Mar 9, 2026

Search Tags:#text-to-speech #elevenlabs #ai voice #voice cloning #voiceover #narration

Ready to run

npx skills add https://github.com/MartinPirate/video-toolkit --skill elevenlabs-martinpirate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: elevenlabs
Source: https://github.com/MartinPirate/video-toolkit/tree/main/.claude/skills/elevenlabs
Command: npx skills add https://github.com/MartinPirate/video-toolkit --skill elevenlabs-martinpirate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, mutagen, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of high-quality AI-generated voiceovers for video content, eliminating the need for manual recording and expensive voice actors.

Core Features & Use Cases

Text-to-Speech Generation: Convert written scripts into natural-sounding speech using various AI voices.
Voice Customization: Adjust parameters like stability, similarity boost, and style for nuanced vocal performance.
Voice Cloning: Create custom voices from audio samples for consistent branding.
Per-Scene Generation: Generate audio for individual video scenes, facilitating seamless integration into editing workflows.
Use Case: Generate narration for a YouTube explainer video, create character voices for an animated short, or produce audio descriptions for accessibility.

Quick Start

Use the elevenlabs skill to generate an MP3 audio file for the text 'Hello, world!' using the Adam voice.

Frequently Asked Questions about elevenlabs

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

FAQPage Schema

How do I generate AI voiceovers from text scripts for video production?▼

To generate AI voiceovers from text scripts, you can use the text-to-speech functionality to convert written content into natural-sounding speech. This supports multiple AI voices, models, and output formats like MP3, facilitating seamless audio creation for video content.

Can I create custom AI voices by cloning audio samples?▼

Yes, you can create custom AI voices by cloning audio samples. This voice cloning feature allows you to generate consistent character voices or branded narration, providing custom voice options for your generated speech.

How do I adjust pacing and pronunciation for AI narration?▼

You can adjust pacing and pronunciation for AI narration using SSML-like pacing control and pronunciation hints. This allows for nuanced vocal performances by modifying parameters such as stability and similarity boost.

Does this text-to-speech tool work with Remotion for video editing?▼

Yes, the text-to-speech generation integrates with Remotion. It supports per-scene audio generation, allowing you to produce individual audio tracks for video scenes and facilitating integration into your editing workflow.

What audio formats and dependencies are needed for AI voice generation?▼

AI voice generation requires the requests and mutagen dependencies to process and handle audio files. The system supports multiple output formats, including MP3, to ensure compatibility with various content generation and playback environments.