mcpField
E
elevenlabs-tts

elevenlabs-tts

github.com/winsorllcCreative & media057 installsUpdated 35w ago
Repository

About elevenlabs-tts

elevenlabs-tts is a command-line skill that turns text into MP3 speech through the ElevenLabs API. It supports voice selection and voice listing, and requires an API key.

Key features

  1. 01Generate speech as MP3
  2. 02Select a voice
  3. 03List available voices
  4. 04Accept SSML input

Use cases

  1. 01Create narrated audio from text
  2. 02Generate accessibility audio
  3. 03Produce chatbot voice responses
  4. 04Create audio notifications

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/winsorllc/upgraded-carnival --skill elevenlabs-tts

After installing, type/elevenlabs-ttsin Claude Code to confirm it loaded.

Bundled fileselevenlabs-tts.js

Details

From the project README

ElevenLabs Text-to-Speech

Generate high-quality speech from text using ElevenLabs API.

Quick Start

/job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js "Hello there" /tmp/output.mp3

Usage

Basic TTS
/job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js "<text>" <output_file>
With Voice Selection
job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js "<text>" <output_file> <voice_id>
List Available Voices
/job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js --list-voices

Configuration

Requires environment variable:

  • ELEVENLABS_API_KEY - ElevenLabs API key

Available Voices

Default voices (get IDs with --list-voices):

  • rachel - Calm, professional female
  • drew - Conversational male
  • clive - Authoritative male
  • bella - Soft female
  • antoni - Versatile male
  • charlie - Energetic male

SSML Support

Use SSML for advanced control:

<speak>
  <break time="1s"/>
  Hello there!
  <break time="500ms"/>
  How can I help you?
</speak>

Output Format

Creates MP3 file at specified path. Returns path on success.

Examples

# Generate speech with default voice
/job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js "Welcome to our service" /tmp/welcome.mp3

# Generate with specific voice
/job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js "This is important" /tmp/alert.mp3 EXAVITQu4vr4xnSDxMaL

# List all available voices
/job/.pi/skills/elevenlabs-tts/elevenlabs-tts.js --list-voices

Tips

  • Keep text under 5000 characters per request
  • Use breaks and pauses for natural speech
  • Preview with short clips before generating long audio
  • For emotional delivery, use voice-specific prompts in the text

When to Use

  • User requests voice message or audio narration
  • Creating accessibility audio content
  • Generating voice responses for chatbots
  • Text-to-speech for notifications

Comments

Markdown supported