Workflows
Blocks
Integrations
ElevenLabs

ElevenLabs Text-to-Speech Block

What is ElevenLabs?

ElevenLabs is like having a professional voice actor that can read any text in realistic, natural-sounding voices. It uses advanced AI to generate high-quality speech from text, perfect for creating voiceovers, audio content, accessibility features, and interactive voice experiences.

When to Use ElevenLabs

Perfect for:

  • Creating podcast episodes and audio content
  • Adding voiceovers to videos and presentations
  • Building accessible apps with text-to-speech
  • Generating multilingual audio content
  • Creating interactive voice responses
  • Audio books and learning materials

Not ideal for:

  • Real-time conversation systems (use speech recognition instead)
  • Simple notification sounds (too advanced/expensive)
  • Background music generation
  • Voice recognition or speech-to-text
  • High-volume, low-cost audio needs

How It Works

  1. Connect to ElevenLabs: Set up your API key and choose voice settings
  2. Provide Text: Input the text you want to convert to speech
  3. Select Voice: Choose from available voices or clone custom ones
  4. Generate Audio: Convert text to high-quality speech
  5. Use Audio: Download, stream, or integrate the generated audio

Real-World Examples

🎙️ Podcast Creation

Blog Article → Extract Text → ElevenLabs TTS → Add Background Music → Publish Podcast

Convert written content into engaging podcast episodes automatically

📚 E-Learning Platform

Course Content → Generate Audio → Create Audio Lessons → Students Listen While Learning

Make educational content accessible and engaging with natural voices

🔊 Accessibility Features

Website Content → User Clicks "Listen" → ElevenLabs TTS → Audio Playback for Visually Impaired

Make websites accessible to users with visual impairments or reading difficulties

📞 Interactive Voice Systems

Customer Query → Generate Response Text → ElevenLabs TTS → Play Audio Response

Create natural-sounding automated phone systems and voice assistants

Easy Setup Guide

🔌 Step 1: ElevenLabs Account Setup

Get Your API Key:

  1. Sign up at ElevenLabs (opens in a new tab)
  2. Go to your profile settings
  3. Generate an API key
  4. Copy the key for use in workflows

Required Information:

  • API Key: Your ElevenLabs authentication key
  • Voice ID: ID of the voice you want to use
  • Model: Text-to-speech model (usually "eleven_monolingual_v1")

⚙️ Step 2: Configure Voice Settings

Basic Configuration:

API_Key = "your-elevenlabs-api-key"
Voice_ID = "21m00Tcm4TlvDq8ikWAM" // Rachel voice
Model = "eleven_monolingual_v1"
Text = "{{text_to_convert}}"

Voice Options:

  • Rachel: Warm, friendly female voice
  • Drew: Professional male voice
  • Clyde: Energetic male voice
  • Bella: Clear, articulate female voice
  • Antoni: Smooth, calm male voice
  • Elli: Young, enthusiastic female voice

🎛️ Step 3: Advanced Settings

Voice Settings:

{
  "stability": 0.5,        // 0-1, higher = more stable
  "similarity_boost": 0.5, // 0-1, higher = more similar to original
  "style": 0.0,           // 0-1, style exaggeration
  "use_speaker_boost": true // Enhance speaker characteristics
}

Output Format:

{
  "output_format": "mp3_44100_128", // Audio quality
  "optimize_streaming_latency": 0,   // 0-4, for real-time use
  "apply_text_normalization": "auto" // Handle numbers, dates, etc.
}

Common Text-to-Speech Operations

📝 Basic Text Conversion

Simple Text to Speech:

Text = "Welcome to our podcast! Today we'll be discussing the future of artificial intelligence and its impact on everyday life."
 
Voice_ID = "21m00Tcm4TlvDq8ikWAM" // Rachel
Model = "eleven_monolingual_v1"
 
// Output: High-quality MP3 audio file

Dynamic Content:

Text = "Hello {{customer_name}}, your order number {{order_id}} has been processed and will be shipped within {{shipping_days}} business days."
 
// Creates personalized audio messages

Multi-paragraph Content:

Text = `Welcome to today's lesson on renewable energy.
 
In this session, we'll explore three main types of renewable energy sources: solar, wind, and hydroelectric power.
 
First, let's discuss solar energy and how photovoltaic cells convert sunlight into electricity.`
 
// Handles long-form content with natural pauses

🎭 Voice Selection and Customization

Different Voices for Different Content:

// Professional announcement
Voice_ID = "Drew" // Professional male voice
Text = "Attention all employees: The quarterly meeting will begin in the main conference room at 2 PM."
 
// Friendly welcome message
Voice_ID = "Rachel" // Warm female voice  
Text = "Hi there! Welcome to our app. Let me show you around and help you get started."
 
// Energetic promotion
Voice_ID = "Clyde" // Energetic male voice
Text = "Don't miss our amazing summer sale! Get up to 50% off on all products this week only!"

Voice Settings Optimization:

// For storytelling (more expressive)
Voice_Settings = {
  "stability": 0.3,        // Less stable = more expressive
  "similarity_boost": 0.7, // Keep voice characteristics
  "style": 0.4            // Add some style variation
}
 
// For professional content (more consistent)
Voice_Settings = {
  "stability": 0.8,        // Very stable
  "similarity_boost": 0.5, // Balanced
  "style": 0.1            // Minimal style variation
}

🌍 Multilingual Content

Multiple Languages:

// English content
Text_EN = "Hello, welcome to our international conference."
Voice_ID = "Rachel"
Model = "eleven_multilingual_v2"
 
// Spanish content  
Text_ES = "Hola, bienvenidos a nuestra conferencia internacional."
Voice_ID = "Spanish_Voice_ID"
Model = "eleven_multilingual_v2"
 
// French content
Text_FR = "Bonjour, bienvenue à notre conférence internationale."
Voice_ID = "French_Voice_ID"  
Model = "eleven_multilingual_v2"

Working with Workflow Data

🎙️ Automated Podcast Generation

// Step 1: Get blog post content
Blog_Content = "{{blog_post_text}}"
 
// Step 2: Create introduction
Intro_Text = "Welcome to Tech Talk Daily. I'm your host, and today we're discussing {{blog_title}}."
 
// Step 3: Generate intro audio
Intro_Audio = elevenlabs_tts({
  "text": Intro_Text,
  "voice_id": "Drew",
  "model": "eleven_monolingual_v1"
})
 
// Step 4: Generate main content audio
Main_Audio = elevenlabs_tts({
  "text": Blog_Content,
  "voice_id": "Rachel",  
  "model": "eleven_monolingual_v1"
})
 
// Step 5: Create outro
Outro_Text = "That's all for today's episode. Don't forget to subscribe and we'll see you next time!"
 
Outro_Audio = elevenlabs_tts({
  "text": Outro_Text,
  "voice_id": "Drew",
  "model": "eleven_monolingual_v1"
})

🏫 Educational Content Creation

// Create course lesson audio
Lesson_Content = `
Chapter 3: Introduction to Machine Learning
 
Machine learning is a subset of artificial intelligence that enables computers to learn and improve from experience without being explicitly programmed.
 
There are three main types of machine learning:
1. Supervised learning
2. Unsupervised learning  
3. Reinforcement learning
 
Let's explore each type in detail.
`
 
Lesson_Audio = elevenlabs_tts({
  "text": Lesson_Content,
  "voice_id": "Bella", // Clear, educational voice
  "model": "eleven_monolingual_v1",
  "voice_settings": {
    "stability": 0.7,
    "similarity_boost": 0.6,
    "style": 0.2
  }
})

📞 Customer Service Automation

// Generate personalized customer messages
Customer_Message = `Hello {{customer_name}}, 
 
This is a friendly reminder that your {{service_type}} subscription will expire on {{expiry_date}}. 
 
To continue enjoying uninterrupted service, please renew your subscription by visiting our website or calling our support team.
 
Thank you for being a valued customer!`
 
Customer_Audio = elevenlabs_tts({
  "text": Customer_Message,
  "voice_id": "Rachel",
  "model": "eleven_monolingual_v1"
})
 
// Save audio for phone system or email attachment

🎯 Marketing and Promotions

// Create promotional audio content
Promo_Text = `
🎉 Special Announcement! 🎉
 
For the next 48 hours only, we're offering an exclusive 40% discount on all premium features!
 
Use code SAVE40 at checkout and transform your business with our powerful tools.
 
But hurry - this incredible offer expires at midnight on {{expiry_date}}.
 
Don't miss out on this amazing opportunity!
`
 
Promo_Audio = elevenlabs_tts({
  "text": Promo_Text,
  "voice_id": "Clyde", // Energetic voice for promotions
  "model": "eleven_monolingual_v1",
  "voice_settings": {
    "stability": 0.5,
    "similarity_boost": 0.6,
    "style": 0.3 // More expressive for marketing
  }
})

Best Practices

For Quality Audio

  • Clear Text: Use proper punctuation and formatting
  • Natural Language: Write as you would speak
  • Appropriate Voice: Match voice to content type
  • Test Settings: Experiment with stability and similarity settings

💰 For Cost Management

  • Optimize Text Length: Remove unnecessary words
  • Batch Processing: Generate multiple audio files together
  • Monitor Usage: Track your character usage
  • Cache Results: Store generated audio for reuse

🎯 For User Experience

  • Consistent Voice: Use the same voice for related content
  • Proper Pacing: Add pauses with punctuation
  • Volume Levels: Ensure consistent audio levels
  • File Formats: Choose appropriate formats for your use case

🔒 For Security

  • API Key Security: Keep your ElevenLabs API key secure
  • Content Review: Review generated content before publication
  • Usage Monitoring: Monitor for unauthorized usage
  • Rate Limiting: Implement proper rate limiting

Common Use Cases

🎧 Audio Content Creation

// Newsletter to podcast conversion
Newsletter_Text = "{{newsletter_content}}"
 
Podcast_Audio = elevenlabs_tts({
  "text": `Welcome to our weekly newsletter podcast. Here are this week's highlights: ${Newsletter_Text}`,
  "voice_id": "Drew",
  "model": "eleven_monolingual_v1"
})

📱 App Accessibility

// Screen reader functionality
Screen_Content = "{{current_screen_text}}"
 
Accessibility_Audio = elevenlabs_tts({
  "text": Screen_Content,
  "voice_id": "Bella", // Clear, articulate voice
  "model": "eleven_monolingual_v1",
  "voice_settings": {
    "stability": 0.8, // Very stable for accessibility
    "similarity_boost": 0.5
  }
})

🎮 Gaming and Interactive Media

// Game character dialogue
Character_Dialogue = "{{character_speech}}"
 
Game_Audio = elevenlabs_tts({
  "text": Character_Dialogue,
  "voice_id": "{{character_voice_id}}",
  "model": "eleven_monolingual_v1",
  "voice_settings": {
    "stability": 0.4, // More expressive for characters
    "similarity_boost": 0.7,
    "style": 0.5 // Add character personality
  }
})

📢 Announcements and Alerts

// Emergency notification
Alert_Text = "Attention: This is an important system maintenance notification. All services will be temporarily unavailable from {{start_time}} to {{end_time}} today."
 
Alert_Audio = elevenlabs_tts({
  "text": Alert_Text,
  "voice_id": "Drew", // Professional, clear voice
  "model": "eleven_monolingual_v1",
  "voice_settings": {
    "stability": 0.9, // Very stable for important messages
    "similarity_boost": 0.5
  }
})

Advanced Features

🎵 Voice Cloning

// Clone a custom voice (requires voice samples)
Custom_Voice_ID = "cloned_voice_{{voice_name}}"
 
Custom_Audio = elevenlabs_tts({
  "text": "{{custom_text}}",
  "voice_id": Custom_Voice_ID,
  "model": "eleven_monolingual_v1"
})

🔊 Streaming Audio

// For real-time applications
Streaming_Settings = {
  "optimize_streaming_latency": 2, // Balance quality and speed
  "output_format": "mp3_22050_32"  // Lower quality for streaming
}

📈 Usage Analytics

// Track usage for optimization
Usage_Data = {
  "characters_used": "{{character_count}}",
  "voice_id": "{{selected_voice}}",
  "generation_time": "{{processing_time}}",
  "audio_duration": "{{audio_length}}"
}

Troubleshooting

API Issues

Authentication Failed:

  • Check your API key is correct and active
  • Verify you have sufficient credits/quota
  • Ensure API key has proper permissions

Voice Not Available:

  • Check if voice ID exists and is accessible
  • Some voices may be premium only
  • Verify voice supports your selected model

🔧 Quality Issues

Robotic or Unnatural Speech:

  • Lower stability setting for more natural variation
  • Check text formatting and punctuation
  • Try different voice that suits your content better

Inconsistent Audio Quality:

  • Use consistent voice settings across generations
  • Ensure text preprocessing is standardized
  • Check audio format settings

Slow Generation:

  • Use appropriate model for your use case
  • Consider optimizing for streaming if needed
  • Check your internet connection

Node Display

The ElevenLabs block shows:

  • Voice Name: Selected voice for text-to-speech
  • Text Preview: First few words of text being converted
  • Audio Duration: Length of generated audio
  • Generation Status: Processing, completed, or error
  • Character Count: Number of characters processed

Ready to bring your text to life with realistic AI voices? ElevenLabs makes it easy to create professional-quality audio content for any application!

Indite Documentation v1.4.0
PrivacyTermsSupport