> ## Documentation Index
> Fetch the complete documentation index at: https://docs.burki.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# ElevenLabs TTS

> Premium voice quality with advanced customization and multilingual support

<Card title="🎭 ElevenLabs: Premium Voice Quality" icon="wand-magic-sparkles">
  Industry-leading TTS with 70+ languages, voice cloning, and granular voice controls. Perfect for high-quality customer interactions and content creation.
</Card>

## Quick Setup

<Steps>
  <Step title="Get API Key">
    1. Visit [ElevenLabs.io](https://elevenlabs.io) and create an account
    2. Navigate to your [API Settings](https://elevenlabs.io/app/settings/api)
    3. Copy your API key
  </Step>

  <Step title="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
  </Step>

  <Step title="Choose Voice & Model">
    Select your preferred model and voice from the dropdowns
  </Step>
</Steps>

<Callout type="info">
  **Free Tier**: ElevenLabs offers 10,000 characters per month on the free plan. Upgrade for higher limits and advanced features.
</Callout>

## Available Models

<Tabs>
  <Tab title="Speed Optimized">
    <CardGroup cols={2}>
      <Card title="⚡ Flash v2.5" icon="bolt">
        **Vendor-reported low latency**

        Ultra-fast model optimized for real-time use

        **Languages**: 70+ languages
        **Best for**: Phone calls, live chat
      </Card>

      <Card title="🚀 Flash v2" icon="rocket">
        **Vendor-reported low latency**

        Fast model (English only, legacy)

        **Languages**: English only
        **Best for**: English-only speed applications
      </Card>
    </CardGroup>
  </Tab>

  <Tab title="Quality Optimized">
    <CardGroup cols={2}>
      <Card title="🌟 Eleven v3" icon="star">
        **\~300ms latency**

        Human-like and expressive speech

        **Languages**: 70+ languages
        **Best for**: Content creation, high-quality needs
      </Card>

      <Card title="🔥 Multilingual v2" icon="globe">
        **\~400ms latency**

        Most lifelike model with rich emotional expression

        **Languages**: 29 languages
        **Best for**: Premium applications
      </Card>
    </CardGroup>
  </Tab>

  <Tab title="Balanced">
    <CardGroup cols={2}>
      <Card title="⚖️ Turbo v2.5" icon="gauge">
        **\~250ms latency**

        High quality with good speed balance

        **Languages**: 70+ languages
        **Best for**: Most business applications
      </Card>

      <Card title="🎙️ TTV v3" icon="microphone">
        **\~300ms latency**

        Voice design model for custom voices

        **Languages**: 70+ languages
        **Best for**: Voice cloning and design
      </Card>
    </CardGroup>
  </Tab>
</Tabs>

<Callout type="tip">
  **Recommendation**: Use **Flash v2.5** for phone calls and **Turbo v2.5** for most other applications.
</Callout>

## Available Voices

### Preset Voices

<Accordion title="Female Voices">
  <CardGroup cols={3}>
    <Card title="Rachel" icon="user">
      **Clear and professional**

      Perfect for business applications

      `Voice ID: 21m00Tcm4TlvDq8ikWAM`
    </Card>

    <Card title="Domi" icon="user">
      **Young and energetic**

      Great for casual conversations

      `Voice ID: AZnzlk1XvdvUeBnXmlld`
    </Card>

    <Card title="Bella" icon="user">
      **Warm and friendly**

      Ideal for customer service

      `Voice ID: EXAVITQu4vr4xnSDxMaL`
    </Card>
  </CardGroup>
</Accordion>

<Accordion title="Male Voices">
  <CardGroup cols={3}>
    <Card title="Antoni" icon="user">
      **Deep and authoritative**

      Professional and commanding

      `Voice ID: ErXwobaYiN019PkySvjV`
    </Card>

    <Card title="Josh" icon="user">
      **Natural and conversational**

      Perfect for casual interactions

      `Voice ID: TxGEqnHWrfWFTfGW9XjX`
    </Card>

    <Card title="Adam" icon="user">
      **Deep and smooth**

      Rich, mature voice

      `Voice ID: pNInz6obpgDQGcFmaJgB`
    </Card>
  </CardGroup>
</Accordion>

<Accordion title="All Available Voices">
  | Voice      | Gender | Style          | Voice ID               | Best For            |
  | ---------- | ------ | -------------- | ---------------------- | ------------------- |
  | **Rachel** | Female | Professional   | `21m00Tcm4TlvDq8ikWAM` | Business calls      |
  | **Domi**   | Female | Energetic      | `AZnzlk1XvdvUeBnXmlld` | Marketing content   |
  | **Bella**  | Female | Friendly       | `EXAVITQu4vr4xnSDxMaL` | Customer service    |
  | **Antoni** | Male   | Authoritative  | `ErXwobaYiN019PkySvjV` | Leadership content  |
  | **Eli**    | Male   | Youthful       | `MF3mGyEYCl7XYWbV9V6O` | Educational content |
  | **Josh**   | Male   | Conversational | `TxGEqnHWrfWFTfGW9XjX` | General purpose     |
  | **Arnold** | Male   | Commanding     | `VR6AewLTigWG4xSOukaG` | Announcements       |
  | **Adam**   | Male   | Smooth         | `pNInz6obpgDQGcFmaJgB` | Storytelling        |
  | **Sam**    | Male   | Approachable   | `yoZ06aMxZJJ28mfd3POQ` | Support calls       |
</Accordion>

## Voice Controls

ElevenLabs offers advanced voice customization options:

<Tabs>
  <Tab title="Stability">
    **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

    ```python theme={null}
    # Example API call
    {
      "stability": 0.5,  # Recommended value
    }
    ```
  </Tab>

  <Tab title="Similarity Boost">
    **Controls voice accuracy** (Range: 0.0 - 1.0)

    * **0.0-0.5**: More creative interpretation
    * **0.6-0.8**: ✅ **Balanced accuracy (Recommended)**
    * **0.9-1.0**: Very close to original voice

    ```python theme={null}
    # Example API call
    {
      "similarity_boost": 0.75,  # Recommended value
    }
    ```
  </Tab>

  <Tab title="Style">
    **Controls speaking style variation** (Range: 0.0 - 1.0)

    * **0.0**: ✅ **Natural baseline voice (Recommended for business)**
    * **0.1-0.5**: Slight style variation
    * **0.6-1.0**: More expressive, dramatic style

    ```python theme={null}
    # Example API call
    {
      "style": 0.0,  # Keep natural for business
    }
    ```
  </Tab>

  <Tab title="Speaker Boost">
    **Enhanced audio quality** (Boolean)

    * ✅ **Enabled (Recommended)**: Boosts voice clarity and reduces background noise
    * Disabled: Standard quality

    Perfect for phone calls and noisy environments.

    ```python theme={null}
    # Example API call
    {
      "use_speaker_boost": true  # Recommended
    }
    ```
  </Tab>
</Tabs>

## Multilingual Support

<Callout type="info">
  **Supported Languages**: ElevenLabs supports 70+ languages with models v3, Flash v2.5, and Turbo v2.5.
</Callout>

<Accordion title="Supported Languages">
  <CardGroup cols={4}>
    <Card title="🇺🇸 English" icon="flag">
      Native support, best quality
    </Card>

    <Card title="🇪🇸 Spanish" icon="flag">
      Excellent quality
    </Card>

    <Card title="🇫🇷 French" icon="flag">
      High quality
    </Card>

    <Card title="🇩🇪 German" icon="flag">
      High quality
    </Card>

    <Card title="🇮🇹 Italian" icon="flag">
      High quality
    </Card>

    <Card title="🇵🇹 Portuguese" icon="flag">
      Good quality
    </Card>

    <Card title="🇵🇱 Polish" icon="flag">
      Good quality
    </Card>

    <Card title="🇨🇳 Chinese" icon="flag">
      Good quality
    </Card>
  </CardGroup>

  **And 62+ more languages including**: Japanese, Korean, Russian, Arabic, Dutch, Turkish, Czech, Hungarian, and many others.
</Accordion>

## Performance Optimization

<Cards>
  <Card title="🚀 Speed Settings" icon="gauge">
    **Latency Optimization (Range: 0-3)**

    * **0**: Ultra Low (Experimental) - \~50ms
    * **1**: ✅ **Low (Recommended)** - fastest vendor profile
    * **2**: Medium - balanced quality/speed profile
    * **3**: High (Most Stable) - \~250ms
  </Card>

  <Card title="📞 Phone Call Setup" icon="phone">
    **Optimal Settings for Calls**

    * **Model**: Flash v2.5
    * **Latency**: 1 (Low)
    * **Stability**: 0.5
    * **Similarity**: 0.75
    * **Speaker Boost**: ✅ Enabled
  </Card>
</Cards>

## API Integration

<CodeGroup>
  ```python Python theme={null}
  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
  ```

  ```javascript JavaScript theme={null}
  const synthesizeSpeech = async (text, voiceId = "21m00Tcm4TlvDq8ikWAM") => {
    const response = await fetch(
      `https://api.elevenlabs.io/v1/text-to-speech/${voiceId}/stream-input`,
      {
        method: "POST",
        headers: {
          "xi-api-key": "your-api-key",
          "Content-Type": "application/json",
        },
        body: JSON.stringify({
          text: text,
          model_id: "eleven_flash_v2_5",
          voice_settings: {
            stability: 0.5,
            similarity_boost: 0.75,
            style: 0.0,
            use_speaker_boost: true,
          },
        }),
      }
    );
    
    return response;
  };
  ```

  ```curl cURL theme={null}
  curl -X POST \
    "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM/stream-input" \
    -H "xi-api-key: your-api-key" \
    -H "Content-Type: application/json" \
    -d '{
      "text": "Hello, this is a test of ElevenLabs TTS.",
      "model_id": "eleven_flash_v2_5",
      "voice_settings": {
        "stability": 0.5,
        "similarity_boost": 0.75,
        "style": 0.0,
        "use_speaker_boost": true
      }
    }'
  ```
</CodeGroup>

## Voice Cloning

<Callout type="info">
  **Professional Voice Cloning**: ElevenLabs offers voice cloning capabilities. Upload voice samples to create custom voices.
</Callout>

<Steps>
  <Step title="Upload Voice Samples">
    Upload 1-25 minutes of clear audio samples of the target voice
  </Step>

  <Step title="Train Custom Voice">
    ElevenLabs processes and creates your custom voice (usually takes a few minutes)
  </Step>

  <Step title="Use Custom Voice ID">
    Use the generated voice ID in your Burki configuration
  </Step>
</Steps>

## Pricing Overview

| Plan        | Characters/Month | Price | Best For                 |
| ----------- | ---------------- | ----- | ------------------------ |
| **Free**    | 10,000           | \$0   | Testing & small projects |
| **Starter** | 30,000           | \$5   | Small businesses         |
| **Creator** | 100,000          | \$22  | Content creators         |
| **Pro**     | 500,000          | \$99  | Professional use         |
| **Scale**   | 2,000,000        | \$330 | Enterprise               |

<Callout type="tip">
  **Cost Optimization**: Use shorter, more focused responses to reduce character usage. Average phone call uses \~2,000 characters.
</Callout>

## Common Issues & Solutions

<Accordion title="Voice Not Available">
  **Problem**: Selected voice doesn't work

  **Solutions**:

  * Verify your plan includes the voice
  * Check voice ID spelling
  * Ensure voice supports your selected model
</Accordion>

<Accordion title="High Latency">
  **Problem**: TTS response is too slow

  **Solutions**:

  * 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
</Accordion>

<Accordion title="Poor Audio Quality">
  **Problem**: Voice sounds robotic or unclear

  **Solutions**:

  * 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
</Accordion>

## See Also

<CardGroup cols={3}>
  <Card title="⚡ Need Speed?" href="/tts-providers/deepgram">
    **Deepgram Aura** - speed-focused TTS for real-time calls
  </Card>

  <Card title="🌍 Multilingual?" href="/tts-providers/inworld">
    **Inworld.ai** - Native voices in 11 languages with emotional markup
  </Card>

  <Card title="🎯 Custom Voices?" href="/tts-providers/resemble">
    **Resemble AI** - Create unlimited custom voices for your brand
  </Card>
</CardGroup>

<Card title="🎛️ Optimization Resources" icon="tools">
  **Fine-tune your ElevenLabs setup:**

  * [Voice Tuning Guide](/tts-providers/voice-tuning) - Master all voice controls
  * [Best Practices](/tts-providers/best-practices) - Performance optimization
  * [Troubleshooting](/tts-providers/troubleshooting) - Fix common issues
</Card>

***

<Card title="🚀 Ready to Use ElevenLabs?" icon="rocket">
  Head back to your [assistant configuration](/ai-configuration) and set up ElevenLabs with these optimized settings!
</Card>