Skip to main content

🎭 ElevenLabs: Premium Voice Quality

Industry-leading TTS with 70+ languages, voice cloning, and granular voice controls. Perfect for high-quality customer interactions and content creation.

​
Quick Setup

1

Get API Key

  1. Visit ElevenLabs.io and create an account
  2. Navigate to your API Settings
  3. Copy your API key
2

Configure in Burki

  1. Go to AI Configuration → TTS tab
  2. Select ElevenLabs as provider
  3. Paste your API key in the TTS API Key field
3

Choose Voice & Model

Select your preferred model and voice from the dropdowns

​
Available Models

  • Speed Optimized
  • Quality Optimized
  • Balanced

⚡ Flash v2.5

~75ms latencyUltra-fast model optimized for real-time useLanguages: 70+ languages Best for: Phone calls, live chat

🚀 Flash v2

~75ms latencyFast model (English only, legacy)Languages: English only Best for: English-only speed applications

​
Available Voices

​
Preset Voices

Rachel

Clear and professionalPerfect for business applicationsVoice ID: 21m00Tcm4TlvDq8ikWAM

Domi

Young and energeticGreat for casual conversationsVoice ID: AZnzlk1XvdvUeBnXmlld

Bella

Warm and friendlyIdeal for customer serviceVoice ID: EXAVITQu4vr4xnSDxMaL

Antoni

Deep and authoritativeProfessional and commandingVoice ID: ErXwobaYiN019PkySvjV

Josh

Natural and conversationalPerfect for casual interactionsVoice ID: TxGEqnHWrfWFTfGW9XjX

Adam

Deep and smoothRich, mature voiceVoice ID: pNInz6obpgDQGcFmaJgB
VoiceGenderStyleVoice IDBest For
RachelFemaleProfessional21m00Tcm4TlvDq8ikWAMBusiness calls
DomiFemaleEnergeticAZnzlk1XvdvUeBnXmlldMarketing content
BellaFemaleFriendlyEXAVITQu4vr4xnSDxMaLCustomer service
AntoniMaleAuthoritativeErXwobaYiN019PkySvjVLeadership content
EliMaleYouthfulMF3mGyEYCl7XYWbV9V6OEducational content
JoshMaleConversationalTxGEqnHWrfWFTfGW9XjXGeneral purpose
ArnoldMaleCommandingVR6AewLTigWG4xSOukaGAnnouncements
AdamMaleSmoothpNInz6obpgDQGcFmaJgBStorytelling
SamMaleApproachableyoZ06aMxZJJ28mfd3POQSupport calls

​
Voice Controls

ElevenLabs offers advanced voice customization options:
  • Stability
  • Similarity Boost
  • Style
  • Speaker Boost
Controls voice consistency (Range: 0.0 - 1.0)
  • 0.0-0.3: More variation, expressive but inconsistent
  • 0.4-0.6: ✅ Balanced consistency (Recommended)
  • 0.7-1.0: Very consistent, may sound monotone
# Example API call
{
  "stability": 0.5,  # Recommended value
}

​
Multilingual Support

🇺🇸 English

Native support, best quality

🇪🇸 Spanish

Excellent quality

🇫🇷 French

High quality

🇩🇪 German

High quality

🇮🇹 Italian

High quality

🇵🇹 Portuguese

Good quality

🇵🇱 Polish

Good quality

🇨🇳 Chinese

Good quality
And 62+ more languages including: Japanese, Korean, Russian, Arabic, Dutch, Turkish, Czech, Hungarian, and many others.

​
Performance Optimization

​
API Integration

import requests

def synthesize_speech(text, voice_id="21m00Tcm4TlvDq8ikWAM"):
    url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream-input"
    
    headers = {
        "xi-api-key": "your-api-key",
        "Content-Type": "application/json"
    }
    
    data = {
        "text": text,
        "model_id": "eleven_flash_v2_5",
        "voice_settings": {
            "stability": 0.5,
            "similarity_boost": 0.75,
            "style": 0.0,
            "use_speaker_boost": True
        }
    }
    
    response = requests.post(url, json=data, headers=headers, stream=True)
    return response

​
Voice Cloning

1

Upload Voice Samples

Upload 1-25 minutes of clear audio samples of the target voice
2

Train Custom Voice

ElevenLabs processes and creates your custom voice (usually takes a few minutes)
3

Use Custom Voice ID

Use the generated voice ID in your Burki configuration

​
Pricing Overview

PlanCharacters/MonthPriceBest For
Free10,000$0Testing & small projects
Starter30,000$5Small businesses
Creator100,000$22Content creators
Pro500,000$99Professional use
Scale2,000,000$330Enterprise

​
Common Issues & Solutions

Problem: Selected voice doesn’t workSolutions:
  • Verify your plan includes the voice
  • Check voice ID spelling
  • Ensure voice supports your selected model
Problem: TTS response is too slowSolutions:
  • Switch to Flash v2.5 model
  • Set latency to 1 (Low)
  • Reduce stability to 0.4-0.5
  • Enable Speaker Boost for clarity without quality loss
Problem: Voice sounds robotic or unclearSolutions:
  • Enable Speaker Boost
  • Adjust similarity_boost to 0.6-0.8
  • Try stability around 0.5
  • Consider upgrading to Turbo v2.5 or v3 model

​
See Also

⚡ Need Speed?

Deepgram Aura - 3x faster with ~75ms latency for real-time calls

🌍 Multilingual?

Inworld.ai - Native voices in 11 languages with emotional markup

🎯 Custom Voices?

Resemble AI - Create unlimited custom voices for your brand

🎛️ Optimization Resources

Fine-tune your ElevenLabs setup:

🚀 Ready to Use ElevenLabs?

Head back to your assistant configuration and set up ElevenLabs with these optimized settings!