ElevenLabs

ElevenLabs implementation for @micdrop/server.

This package provides high-quality real-time text-to-speech implementation using ElevenLabs’ streaming API.

Installation

npm install @micdrop/elevenlabs

ElevenLabs TTS (Text-to-Speech)

Usage

import { ElevenLabsTTS } from '@micdrop/elevenlabs'
import { MicdropServer } from '@micdrop/server'

const tts = new ElevenLabsTTS({
  apiKey: process.env.ELEVENLABS_API_KEY || '',
  voiceId: '21m00Tcm4TlvDq8ikWAM', // ElevenLabs voice ID
  modelId: 'eleven_turbo_v2_5', // Optional: model to use
  language: 'en', // Optional: language code
  voiceSettings: {
    stability: 0.5,
    similarity_boost: 0.75,
    style: 0.5,
  },
})

// Use with MicdropServer
new MicdropServer(socket, {
  tts,
  // ... other options
})

Options

Option	Type	Default	Description
`apiKey`	`string`	Required	Your ElevenLabs API key
`voiceId`	`string`	Required	ElevenLabs voice ID
`modelId`	`'eleven_multilingual_v2' \| 'eleven_turbo_v2_5' \| 'eleven_flash_v2_5'`	`'eleven_turbo_v2_5'`	Model to use for speech synthesis
`language`	`string`	Optional	Language code (e.g., ‘en’, ‘fr’)
`outputFormat`	`TextToSpeechStreamRequestOutputFormat`	`'pcm_16000'`	Audio output format
`voiceSettings`	`VoiceSettings`	Optional	Voice customization settings
`connectionTimeout`	`number`	`5000`	Timeout in milliseconds for WebSocket connection
`retryDelay`	`number`	`1000`	Delay in milliseconds between reconnection attempts
`maxRetry`	`number`	`3`	Maximum number of reconnection attempts before failing

Voice Settings

The voiceSettings option allows you to customize the voice characteristics:

const tts = new ElevenLabsTTS({
  apiKey: 'your-api-key',
  voiceId: 'your-voice-id',
  voiceSettings: {
    stability: 0.5, // 0.0 to 1.0 - Lower = more variable, Higher = more stable
    similarity_boost: 0.75, // 0.0 to 1.0 - How closely to match the original voice
    style: 0.5, // 0.0 to 1.0 - Exaggeration of the style
    use_speaker_boost: true, // Boost the similarity to the speaker
  },
})

Supported Models

Model	Description	Languages	Speed
`eleven_multilingual_v2`	High-quality multilingual model	29+ languages	Standard
`eleven_turbo_v2_5`	Fast, high-quality model optimized for speed	English	Fast
`eleven_flash_v2_5`	Ultra-fast model for real-time applications	English	Very Fast

Supported Languages

ElevenLabs supports 29+ languages including:

Code	Language	Code	Language	Code	Language
`en`	English	`es`	Spanish	`fr`	French
`de`	German	`it`	Italian	`pt`	Portuguese
`pl`	Polish	`tr`	Turkish	`ru`	Russian
`nl`	Dutch	`cs`	Czech	`ar`	Arabic
`zh`	Chinese	`ja`	Japanese	`hu`	Hungarian
`ko`	Korean	`hi`	Hindi	`fi`	Finnish

Getting Started

Sign up for an ElevenLabs account and get your API key
Choose a voice from the ElevenLabs voice library or create a custom voice
Install the package and configure with your credentials

import { ElevenLabsTTS } from '@micdrop/elevenlabs'

const tts = new ElevenLabsTTS({
  apiKey: 'your-elevenlabs-api-key',
  voiceId: 'your-voice-id', // Get this from ElevenLabs dashboard
  modelId: 'eleven_turbo_v2_5', // Choose based on your needs
  language: 'en',
  voiceSettings: {
    stability: 0.5,
    similarity_boost: 0.75,
  },
})

// Use with MicdropServer
new MicdropServer(socket, {
  tts,
  // ... other options
})

Finding Voice IDs

You can find voice IDs in several ways:

ElevenLabs Dashboard: Browse voices in your ElevenLabs account
Voice Library: Use the public voice library API