> ## 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.

# Voice Tuning & Customization

> Master voice controls across all TTS providers for optimal speech quality and personality

<Card title="🎛️ Voice Tuning Mastery" icon="sliders">
  Fine-tune voice characteristics across all TTS providers to create the perfect voice experience for your application. Learn stability, similarity, style, and provider-specific controls.
</Card>

## Overview of Voice Controls

<Card title="🎯 Universal Voice Parameters" icon="target">
  While each provider has unique features, these core concepts apply across most TTS services.
</Card>

<CardGroup cols={3}>
  <Card title="🎚️ Stability" icon="gauge">
    **Voice Consistency**

    Controls how consistent the voice sounds across different sentences

    *Available: ElevenLabs*
  </Card>

  <Card title="🎯 Similarity" icon="crosshairs">
    **Voice Accuracy**

    How closely the output matches the original voice characteristics

    *Available: ElevenLabs*
  </Card>

  <Card title="🎭 Style/Expression" icon="masks-theater">
    **Speaking Style**

    Emotional expression and speaking style variation

    *Available: ElevenLabs, Inworld*
  </Card>
</CardGroup>

## Provider-Specific Controls

<Tabs>
  <Tab title="ElevenLabs">
    <Card title="🎭 ElevenLabs Voice Controls" icon="wand-magic-sparkles">
      The most comprehensive voice tuning options available.
    </Card>

    ### Stability (0.0 - 1.0)

    **Controls voice consistency across sentences**

    <Accordion title="Stability Settings Guide">
      | Range       | Effect                           | Best For                         | Example                              |
      | ----------- | -------------------------------- | -------------------------------- | ------------------------------------ |
      | **0.0-0.2** | Very expressive, inconsistent    | Creative content, storytelling   | Audiobooks with character voices     |
      | **0.3-0.4** | Expressive with some variation   | Marketing content, presentations | Sales pitches, educational content   |
      | **0.5-0.6** | ✅ **Balanced (Recommended)**     | Business applications            | Customer service, professional calls |
      | **0.7-0.8** | Very consistent, less expressive | Technical content, instructions  | Help desk, documentation             |
      | **0.9-1.0** | Extremely consistent, monotone   | Announcements, alerts            | System notifications, alerts         |
    </Accordion>

    ```json theme={null}
    {
      "stability": 0.5,  // Recommended starting point
      "use_case": "balanced_professional"
    }
    ```

    ### Similarity Boost (0.0 - 1.0)

    **Controls how accurately the voice matches the original**

    <Accordion title="Similarity Settings Guide">
      | Range        | Effect                      | Best For                | Trade-off                           |
      | ------------ | --------------------------- | ----------------------- | ----------------------------------- |
      | **0.0-0.4**  | Creative interpretation     | Unique voice variations | Less like original voice            |
      | **0.5-0.7**  | Balanced accuracy           | Most applications       | Good balance of creativity/accuracy |
      | **0.75**     | ✅ **Optimal (Recommended)** | Production use          | Best overall quality                |
      | **0.8-0.9**  | Very accurate               | Brand consistency       | May sound slightly robotic          |
      | **0.95-1.0** | Extremely accurate          | Voice cloning           | Potential quality degradation       |
    </Accordion>

    ```json theme={null}
    {
      "similarity_boost": 0.75,  // Sweet spot for most uses
      "note": "Recommended by ElevenLabs"
    }
    ```

    ### Style (0.0 - 1.0)

    **Controls speaking style and expressiveness**

    <Accordion title="Style Settings Guide">
      | Range       | Effect                  | Best For          | Personality                   |
      | ----------- | ----------------------- | ----------------- | ----------------------------- |
      | **0.0**     | ✅ **Natural baseline**  | Business calls    | Professional, neutral         |
      | **0.1-0.3** | Slight style variation  | Customer service  | Friendly, approachable        |
      | **0.4-0.6** | Moderate expression     | Marketing content | Engaging, enthusiastic        |
      | **0.7-0.9** | High expressiveness     | Entertainment     | Dramatic, animated            |
      | **1.0**     | Maximum style variation | Character voices  | Highly expressive, theatrical |
    </Accordion>

    ```json theme={null}
    {
      "style": 0.0,  // Keep at 0.0 for business applications
      "business_rule": "Higher values can sound unprofessional"
    }
    ```

    ### Speaker Boost

    **Enhanced audio quality and clarity**

    <CardGroup cols={2}>
      <Card title="✅ Enabled (Recommended)" icon="volume-high">
        **Benefits:**

        * Clearer voice quality
        * Reduced background noise
        * Better phone call clarity
        * Enhanced speech intelligibility

        **Best for:** All applications
      </Card>

      <Card title="❌ Disabled" icon="volume-low">
        **When to use:**

        * Specific audio pipeline requirements
        * Custom post-processing needs
        * Legacy system compatibility

        **Trade-off:** Lower audio quality
      </Card>
    </CardGroup>

    ### Latency Optimization (0-3)

    | Setting | Latency                      | Quality | Best For                        |
    | ------- | ---------------------------- | ------- | ------------------------------- |
    | **0**   | \~50ms                       | Lower   | Experimental ultra-low latency  |
    | **1**   | ✅ **Fastest vendor profile** | Good    | ✅ **Phone calls (Recommended)** |
    | **2**   | Balanced vendor profile      | Better  | General applications            |
    | **3**   | \~250ms                      | Best    | High-quality content creation   |
  </Tab>

  <Tab title="Inworld.ai">
    <Card title="🎭 Inworld Emotional Controls" icon="masks-theater">
      Emotional markup and contextual expression controls.
    </Card>

    ### Emotional Markup

    **Direct emotional control through text tags**

    <Accordion title="Basic Emotions">
      ```markdown theme={null}
      [happy] Great to hear from you!
      [sad] I'm sorry about that issue.
      [excited] This is fantastic news!
      [concerned] Let me help you with that.
      [confident] I can definitely assist you.
      [grateful] Thank you for your patience.
      ```

      **Best Practices:**

      * Use 1-2 emotion tags per sentence maximum
      * Match emotions to content context
      * Test different emotions with your chosen voice
      * Don't overuse - natural text is still important
    </Accordion>

    <Accordion title="Speaking Styles">
      ```markdown theme={null}
      [whispering] This is confidential information.
      [emphasizing] This is VERY important.
      [casual] Hey there, how's it going?
      [professional] Thank you for contacting our office.
      [friendly] I'm happy to help you today!
      ```

      **Usage Guidelines:**

      * Use styles that match your brand voice
      * Consider your audience and context
      * Test styles with different voices
      * Combine with basic emotions carefully
    </Accordion>

    ### Language-Specific Tuning

    | Language    | Voice Recommendations | Emotional Range | Production Ready |
    | ----------- | --------------------- | --------------- | ---------------- |
    | **English** | Ashley, Alex, Aria    | Full range      | ✅ Production     |
    | **Spanish** | Diego, Lupita         | Good range      | ✅ Production     |
    | **French**  | Hélène, Mathieu       | Good range      | ✅ Production     |
    | **German**  | Johanna, Josef        | Limited range   | 🟡 Beta          |
    | **Chinese** | Yichen, Xiaoyin       | Limited range   | 🟡 Beta          |
    | **Other**   | Various               | Basic range     | 🟡 Beta          |

    ### Model Selection for Expression

    <CardGroup cols={2}>
      <Card title="inworld-tts-1" icon="star">
        **Balanced Expression**

        * Good emotional range
        * Consistent quality
        * ✅ Recommended for business
        * \~200ms latency
      </Card>

      <Card title="inworld-tts-1.5-max" icon="sparkles">
        **Maximum Expression**

        * Enhanced emotional range
        * More dramatic expressions
        * Best for creative content
        * \~250ms latency
      </Card>
    </CardGroup>
  </Tab>

  <Tab title="Deepgram & Resemble">
    <Card title="⚡ Speed-Focused Providers" icon="bolt">
      These providers focus on speed and custom voices rather than extensive tuning options.
    </Card>

    ### Deepgram Aura

    **Limited but effective controls:**

    <Accordion title="Voice Selection Strategy">
      **Choose the right voice for your use case:**

      | Voice       | Personality        | Best For            |
      | ----------- | ------------------ | ------------------- |
      | **Asteria** | Warm, professional | Customer service    |
      | **Luna**    | Soft, gentle       | Healthcare, support |
      | **Stella**  | Clear, bright      | Announcements       |
      | **Orion**   | Authoritative      | Business calls      |
      | **Helios**  | Energetic          | Marketing           |
      | **Thalia**  | Professional       | Corporate           |
    </Accordion>

    <Accordion title="Audio Format Optimization">
      **Phone calls:**

      ```json theme={null}
      {
        "encoding": "mulaw",
        "sample_rate": 8000,
        "voice": "aura-asteria-en"
      }
      ```

      **High quality:**

      ```json theme={null}
      {
        "encoding": "linear16",
        "sample_rate": 24000,
        "voice": "aura-2-thalia-en"
      }
      ```
    </Accordion>

    ### Resemble AI

    **Custom voice optimization:**

    <Accordion title="Voice Training Quality">
      **Optimize your custom voice training:**

      * **Training Data**: 3-10 minutes of clear speech
      * **Consistency**: Same speaker, environment, microphone
      * **Content**: Diverse sentences and emotions
      * **Quality**: Clean audio, minimal background noise

      ```python theme={null}
      # Voice training optimization
      training_guidelines = {
          "duration": "3-10 minutes",
          "sample_rate": "22kHz or higher",
          "format": "WAV (preferred) or MP3",
          "content": "diverse_sentences_with_emotions",
          "environment": "quiet_professional_setting"
      }
      ```
    </Accordion>

    <Accordion title="Streaming Configuration">
      **WebSocket streaming optimization:**

      ```json theme={null}
      {
        "sample_rate": 8000,
        "precision": "MULAW",
        "output_format": "wav",
        "streaming": true
      }
      ```

      **Best for phone calls and real-time applications**
    </Accordion>
  </Tab>
</Tabs>

## Recommended Settings by Use Case

<Tabs>
  <Tab title="Phone Calls">
    <Card title="📞 Phone Call Optimization" icon="phone">
      Settings optimized for clear, professional phone conversations.
    </Card>

    ### ElevenLabs Phone Setup

    ```json theme={null}
    {
      "model": "eleven_flash_v2_5",
      "voice": "rachel",
      "stability": 0.5,
      "similarity_boost": 0.75,
      "style": 0.0,
      "use_speaker_boost": true,
      "latency": 1
    }
    ```

    ### Deepgram Phone Setup

    ```json theme={null}
    {
      "model": "aura-2-asteria-en",
      "encoding": "mulaw",
      "sample_rate": 8000
    }
    ```

    ### Inworld Phone Setup

    ```json theme={null}
    {
      "model": "inworld-tts-1",
      "voice": "Ashley",
      "language": "en",
      "text": "[professional] Thank you for calling. [helpful] How may I assist you?"
    }
    ```

    **Key Principles:**

    * Prioritize clarity over expressiveness
    * Use phone-compatible audio formats
    * Keep emotional variation moderate
    * Enable speaker boost when available
  </Tab>

  <Tab title="Customer Service">
    <Card title="🎧 Customer Service Excellence" icon="headset">
      Warm, helpful, and professional voice settings.
    </Card>

    ### ElevenLabs Customer Service

    ```json theme={null}
    {
      "voice": "bella",
      "stability": 0.6,
      "similarity_boost": 0.75,
      "style": 0.1,
      "use_speaker_boost": true
    }
    ```

    ### Inworld Customer Service

    ```markdown theme={null}
    [friendly] Hello! [helpful] I'm here to assist you today. 
    [understanding] I completely understand your concern. 
    [confident] I can definitely help you resolve this.
    ```

    **Voice Selection:**

    * **ElevenLabs**: Bella (warm), Rachel (professional)
    * **Deepgram**: Asteria (warm), Luna (gentle)
    * **Inworld**: Ashley (friendly), Aria (professional)
    * **Resemble**: Custom friendly customer service voice

    **Key Principles:**

    * Warm and approachable tone
    * Consistent but not monotone
    * Slight emotional variation for empathy
    * Clear pronunciation for understanding
  </Tab>

  <Tab title="Content Creation">
    <Card title="🎬 Content & Media" icon="video">
      Engaging, expressive settings for videos, podcasts, and presentations.
    </Card>

    ### ElevenLabs Content Creation

    ```json theme={null}
    {
      "model": "eleven_v3",
      "voice": "antoni",
      "stability": 0.4,
      "similarity_boost": 0.7,
      "style": 0.3,
      "use_speaker_boost": true,
      "latency": 2
    }
    ```

    ### Inworld Content Creation

    ```markdown theme={null}
    [excited] Welcome to our latest episode! 
    [curious] Have you ever wondered about this topic? 
    [explaining] Let me break this down for you.
    ```

    **Voice Selection:**

    * **ElevenLabs**: Antoni (authoritative), Bella (engaging)
    * **Inworld**: Hades (dramatic), Aria (professional)
    * **Resemble**: Custom brand spokesperson voice

    **Key Principles:**

    * Higher expressiveness acceptable
    * Quality over speed
    * Match voice to content personality
    * Use emotional variation for engagement
  </Tab>

  <Tab title="Multilingual Apps">
    <Card title="🌍 Global Applications" icon="globe">
      Settings optimized for multiple languages and international audiences.
    </Card>

    ### ElevenLabs Multilingual

    ```json theme={null}
    {
      "model": "eleven_v3",
      "language": "es",
      "stability": 0.5,
      "similarity_boost": 0.75,
      "style": 0.0
    }
    ```

    ### Inworld Multilingual

    ```json theme={null}
    {
      "voice": "Diego",
      "language": "es",
      "text": "[amigable] ¡Hola! [servicial] ¿Cómo puedo ayudarte?"
    }
    ```

    **Language-Specific Recommendations:**

    | Language    | Provider           | Voice          | Notes                  |
    | ----------- | ------------------ | -------------- | ---------------------- |
    | **Spanish** | ElevenLabs/Inworld | Rachel/Diego   | Native pronunciation   |
    | **French**  | ElevenLabs/Inworld | Bella/Hélène   | Natural accent         |
    | **German**  | ElevenLabs/Inworld | Antoni/Johanna | Clear pronunciation    |
    | **Chinese** | Inworld            | Yichen/Xiaoyin | Mandarin optimized     |
    | **English** | All providers      | Various        | Best quality available |

    **Key Principles:**

    * Use native voices when available
    * Test pronunciation with native speakers
    * Consider cultural communication styles
    * Adjust formality levels appropriately
  </Tab>
</Tabs>

## Voice Testing & Optimization

<Card title="🧪 Systematic Voice Testing" icon="flask">
  Develop a systematic approach to test and optimize your voice settings.
</Card>

### Testing Framework

<Steps>
  <Step title="Baseline Testing">
    Test with provider default settings using your actual content
  </Step>

  <Step title="Parameter Sweeping">
    Systematically adjust one parameter at a time
  </Step>

  <Step title="A/B Testing">
    Compare different settings with real users or stakeholders
  </Step>

  <Step title="Production Monitoring">
    Monitor voice quality and user feedback in live applications
  </Step>

  <Step title="Iterative Improvement">
    Continuously refine based on real-world usage data
  </Step>
</Steps>

### Testing Script Examples

<CodeGroup>
  ```python ElevenLabs Testing theme={null}
  def test_elevenlabs_settings():
      test_cases = [
          {
              "name": "Conservative Business",
              "settings": {
                  "stability": 0.6,
                  "similarity_boost": 0.75,
                  "style": 0.0,
                  "use_speaker_boost": True
              }
          },
          {
              "name": "Balanced Professional", 
              "settings": {
                  "stability": 0.5,
                  "similarity_boost": 0.75,
                  "style": 0.1,
                  "use_speaker_boost": True
              }
          },
          {
              "name": "Expressive Friendly",
              "settings": {
                  "stability": 0.4,
                  "similarity_boost": 0.7,
                  "style": 0.2,
                  "use_speaker_boost": True
              }
          }
      ]
      
      test_text = "Hello! Thank you for calling our customer service line. How may I assist you today?"
      
      for test_case in test_cases:
          print(f"Testing: {test_case['name']}")
          # Generate audio with settings
          # Collect feedback or metrics
  ```

  ```python Inworld Testing   theme={null}
  def test_inworld_emotions():
      emotion_tests = [
          "[professional] Thank you for calling our support line.",
          "[friendly] Hi there! How can I help you today?",
          "[helpful] I'd be happy to assist you with that.",
          "[understanding] I completely understand your concern.",
          "[confident] I can definitely resolve this for you."
      ]
      
      voices = ["Ashley", "Alex", "Aria"]
      
      for voice in voices:
          for emotion_text in emotion_tests:
              print(f"Testing {voice}: {emotion_text}")
              # Generate and evaluate audio
  ```

  ```python Multi-Provider Testing theme={null}
  def compare_providers():
      test_text = "Welcome to our service. How may I help you today?"
      
      provider_configs = {
          "elevenlabs": {
              "voice": "rachel",
              "stability": 0.5,
              "similarity_boost": 0.75
          },
          "deepgram": {
              "voice": "aura-asteria-en"
          },
          "inworld": {
              "voice": "Ashley",
              "text": "[professional] " + test_text
          }
      }
      
      # Test each provider and collect metrics
      for provider, config in provider_configs.items():
          print(f"Testing {provider}")
          # Generate audio and measure:
          # - Latency
          # - Audio quality
          # - User preference
  ```
</CodeGroup>

## Common Tuning Mistakes

<Card title="⚠️ Avoid These Pitfalls" icon="triangle-exclamation">
  Learn from common voice tuning mistakes to save time and improve results.
</Card>

<Accordion title="Over-Optimization">
  **Problem**: Adjusting too many parameters at once

  **Solution**:

  * Change one parameter at a time
  * Test each change thoroughly
  * Keep notes on what works
  * Use A/B testing for comparisons

  **Example**: Don't change stability, similarity, and style simultaneously
</Accordion>

<Accordion title="Extreme Settings">
  **Problem**: Using values at the far ends of ranges (0.0 or 1.0)

  **Solution**:

  * Start with recommended ranges
  * Use extreme values only for specific effects
  * Test thoroughly before production use
  * Consider user experience impact

  **Example**: `style: 1.0` often sounds unnatural for business use
</Accordion>

<Accordion title="Ignoring Use Case">
  **Problem**: Using the same settings for different applications

  **Solution**:

  * Create setting profiles for different use cases
  * Consider your audience and context
  * Test with actual content types
  * Adjust based on user feedback

  **Example**: Phone call settings ≠ podcast settings
</Accordion>

<Accordion title="Neglecting Voice Selection">
  **Problem**: Focusing only on parameters, ignoring voice choice

  **Solution**:

  * Voice selection is often more important than fine-tuning
  * Test multiple voices with your content
  * Consider voice personality match
  * Use provider recommendations

  **Example**: Wrong voice + perfect settings \< Right voice + default settings
</Accordion>

## Advanced Optimization Techniques

<Tabs>
  <Tab title="Dynamic Settings">
    **Adjust settings based on context or content type**

    ```python theme={null}
    class DynamicVoiceSettings:
        def __init__(self):
            self.settings_profiles = {
                "greeting": {
                    "stability": 0.6,
                    "style": 0.1,
                    "emotion": "[friendly]"
                },
                "problem_solving": {
                    "stability": 0.5,
                    "style": 0.0,
                    "emotion": "[helpful]"
                },
                "closing": {
                    "stability": 0.5,
                    "style": 0.1,
                    "emotion": "[grateful]"
                }
            }
            
        def get_settings(self, context):
            return self.settings_profiles.get(context, self.settings_profiles["greeting"])
    ```
  </Tab>

  <Tab title="Content-Aware Tuning">
    **Adjust based on content analysis**

    ```python theme={null}
    def analyze_and_tune(text):
        # Analyze content characteristics
        word_count = len(text.split())
        has_questions = '?' in text
        has_exclamations = '!' in text
        formality_score = calculate_formality(text)
        
        # Adjust settings based on analysis
        if formality_score > 0.8:
            return {"stability": 0.6, "style": 0.0}
        elif has_exclamations:
            return {"stability": 0.4, "style": 0.2}
        elif has_questions:
            return {"stability": 0.5, "style": 0.1}
        else:
            return {"stability": 0.5, "style": 0.0}
    ```
  </Tab>

  <Tab title="User Preference Learning">
    **Learn from user feedback and behavior**

    ```python theme={null}
    class VoicePreferenceLearner:
        def __init__(self):
            self.feedback_data = []
            self.current_settings = default_settings()
            
        def record_feedback(self, settings, rating, context):
            self.feedback_data.append({
                "settings": settings,
                "rating": rating,
                "context": context,
                "timestamp": time.now()
            })
            
        def optimize_settings(self):
            # Analyze feedback patterns
            # Adjust settings based on highest-rated combinations
            # Return optimized settings
            pass
    ```
  </Tab>
</Tabs>

## Related Guides

<CardGroup cols={2}>
  <Card title="📚 Provider Guides" icon="book">
    **Detailed Provider Information:**

    * [ElevenLabs Setup](/tts-providers/elevenlabs) - Premium quality controls
    * [Deepgram Configuration](/tts-providers/deepgram) - Speed optimization
    * [Inworld Emotions](/tts-providers/inworld) - Emotional markup
    * [Resemble Custom Voices](/tts-providers/resemble) - Brand voice creation
  </Card>

  <Card title="🛠️ Advanced Topics" icon="tools">
    **Next Steps:**

    * [Troubleshooting Guide](/tts-providers/troubleshooting) - Fix common issues
    * [Best Practices](/tts-providers/best-practices) - Production optimization
    * [AI Configuration](/ai-configuration) - System-wide settings
  </Card>
</CardGroup>

***

<Card title="🎯 Perfect Your Voice Settings" icon="bullseye">
  Use this guide to systematically optimize your TTS voice settings. Start with recommended defaults, test systematically, and refine based on your specific use case and user feedback.
</Card>