> ## 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.

# Inworld.ai TTS

> AI-powered TTS with emotional expression, multilingual support, and zero-shot voice cloning

<Card title="🎭 Inworld.ai: AI-Powered Expression" icon="masks-theater">
  Advanced AI-driven TTS with emotional markup, context awareness, and support for 11-15 languages depending on the selected model. Perfect for gaming, entertainment, and expressive customer interactions.
</Card>

## Quick Setup

<Steps>
  <Step title="Get API Key">
    1. Visit [Inworld Studio](https://studio.inworld.ai) and create an account
    2. Navigate to **Integrations** → **API Keys**
    3. Generate a new API key for TTS
    4. Copy your Bearer token
  </Step>

  <Step title="Configure in Burki">
    1. Go to **AI Configuration** → **TTS** tab
    2. Select **Inworld.ai** as provider
    3. Paste your Bearer token in the **TTS API Key** field
  </Step>

  <Step title="Choose Model & Voice">
    Select an exact model ID such as `inworld-tts-1`, `inworld-tts-1-max`, `inworld-tts-1.5-max`, or `inworld-tts-1.5-mini`.
  </Step>
</Steps>

<Callout type="info">
  **Free Tier**: Inworld offers free credits for testing. Includes access to all voices and emotional markup features.
</Callout>

## Available Models

<CardGroup cols={2}>
  <Card title="🎪 inworld-tts-1" icon="star">
    **\~200ms latency**

    Flagship model with realistic, context-aware synthesis

    **Languages**: 11 supported languages
    **Best for**: Production applications, customer service
  </Card>

  <Card title="🔬 inworld-tts-1-max" icon="flask">
    **\~250ms latency**

    Larger, more expressive model (experimental)

    **Languages**: 11 supported languages
    **Best for**: Creative content, gaming, entertainment
  </Card>

  <Card title="✨ inworld-tts-1.5-max" icon="sparkles">
    **\~200ms latency**

    Rich, expressive, contextually aware 1.5 generation model

    **Languages**: 15 supported languages
    **Best for**: Expressive production applications
  </Card>

  <Card title="⚡ inworld-tts-1.5-mini" icon="bolt">
    **\~120ms latency**

    Ultra-fast, lower-cost 1.5 generation model

    **Languages**: 15 supported languages
    **Best for**: Latency-sensitive calls
  </Card>
</CardGroup>

<Callout type="tip">
  **Recommendation**: Use `inworld-tts-1.5-mini` when latency is the priority, `inworld-tts-1.5-max` for richer expression, or `inworld-tts-1` for the stable default path.
</Callout>

## Supported Language Codes

`inworld-tts-1` and `inworld-tts-1-max` support `en`, `zh`, `ko`, `nl`, `fr`, `es`, `ja`, `de`, `it`, `pl`, and `pt`.

`inworld-tts-1.5-max` and `inworld-tts-1.5-mini` additionally support `hi`, `ru`, `he`, and `ar`.

## Multilingual Voice Library

<Tabs>
  <Tab title="English">
    <CardGroup cols={2}>
      <Card title="Hades" icon="user">
        **Deep and commanding**

        Perfect for authoritative characters

        `Voice ID: Hades`
      </Card>

      <Card title="Alex" icon="user">
        **Clear and natural**

        Great for professional applications

        `Voice ID: Alex`
      </Card>

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

        Ideal for customer service

        `Voice ID: Ashley`
      </Card>

      <Card title="Aria" icon="user">
        **Professional and articulate**

        Perfect for business communications

        `Voice ID: Aria`
      </Card>
    </CardGroup>
  </Tab>

  <Tab title="Spanish">
    <CardGroup cols={2}>
      <Card title="Diego" icon="user">
        **Warm and expressive**

        Native Spanish male voice

        `Voice ID: Diego`
      </Card>

      <Card title="Lupita" icon="user">
        **Elegant and clear**

        Professional Spanish female voice

        `Voice ID: Lupita`
      </Card>

      <Card title="Miguel" icon="user">
        **Strong and confident**

        Authoritative Spanish male voice

        `Voice ID: Miguel`
      </Card>

      <Card title="Rafael" icon="user">
        **Smooth and professional**

        Business-ready Spanish voice

        `Voice ID: Rafael`
      </Card>
    </CardGroup>
  </Tab>

  <Tab title="French">
    <CardGroup cols={2}>
      <Card title="Alain" icon="user">
        **Sophisticated male voice**

        Native French pronunciation

        `Voice ID: Alain`
      </Card>

      <Card title="Hélène" icon="user">
        **Graceful and articulate**

        Professional French female voice

        `Voice ID: Hélène`
      </Card>

      <Card title="Mathieu" icon="user">
        **Clear and natural**

        Conversational French voice

        `Voice ID: Mathieu`
      </Card>

      <Card title="Étienne" icon="user">
        **Expressive and warm**

        Engaging French male voice

        `Voice ID: Étienne`
      </Card>
    </CardGroup>
  </Tab>

  <Tab title="Other Languages">
    <Accordion title="German">
      * **Johanna** (Female) - `Voice ID: Johanna` - Precise and professional
      * **Josef** (Male) - `Voice ID: Josef` - Strong and clear
    </Accordion>

    <Accordion title="Chinese (Mandarin)">
      * **Yichen** (Male) - `Voice ID: Yichen` - Natural and expressive
      * **Xiaoyin** (Female) - `Voice ID: Xiaoyin` - Melodic and clear
      * **Xinyi** (Female) - `Voice ID: Xinyi` - Gentle and articulate
      * **Jing** (Female) - `Voice ID: Jing` - Smooth and professional
    </Accordion>

    <Accordion title="Japanese">
      * **Hiroshi** (Male) - `Voice ID: Hiroshi` - Polite and clear
      * **Sakura** (Female) - `Voice ID: Sakura` - Gentle and melodic
    </Accordion>

    <Accordion title="Other Supported Languages">
      * **Italian**: Marco (Male), Giulia (Female)
      * **Portuguese**: Joao (Male), Ana (Female)
      * **Dutch**: Jan (Male), Emma (Female)
      * **Korean**: Min (Male), Soo (Female)
      * **Polish**: Piotr (Male), Anna (Female)
    </Accordion>
  </Tab>
</Tabs>

## Emotional Markup System

<Card title="🎭 Express Emotions in Speech" icon="heart">
  Inworld's unique emotional markup allows you to add feelings and speaking styles directly in your text.
</Card>

### Emotional Tags

<Tabs>
  <Tab title="Basic Emotions">
    ```markdown theme={null}
    [happy] I'm excited to help you today!
    [sad] I'm sorry to hear about that issue.
    [angry] This is completely unacceptable!
    [surprised] Wow, I didn't expect that!
    [fearful] Please be careful with that.
    [disgusted] That's not what I ordered.
    ```

    **Available emotions**: happy, sad, angry, surprised, fearful, disgusted, neutral
  </Tab>

  <Tab title="Speaking Styles">
    ```markdown theme={null}
    [whispering] This is confidential information.
    [shouting] ATTENTION EVERYONE!
    [laughing] That's hilarious!
    [crying] I can't believe this happened.
    [sighing] I suppose we have no choice.
    [breathing] Take a deep breath and relax.
    ```

    **Available styles**: whispering, shouting, laughing, crying, sighing, breathing
  </Tab>

  <Tab title="Advanced Examples">
    ```markdown theme={null}
    # Mixed emotions in conversation
    [happy] Welcome to our store! [surprised] Oh, you're looking for that specific item? [sad] Unfortunately, we're out of stock right now, [happy] but I can order it for you!

    # Style changes for emphasis
    [normal] The meeting will start at [emphasizing] three o'clock sharp. [whispering] Don't be late again.

    # Character voices for gaming
    [angry] You dare challenge me? [laughing] This will be easy! [confident] Prepare for battle!
    ```
  </Tab>
</Tabs>

<Callout type="tip">
  **Pro Tip**: Emotional markup works best with natural sentence structure. Don't overuse tags - less is often more effective.
</Callout>

## Zero-Shot Voice Cloning

<Card title="🎯 Custom Voice Creation" icon="wand-magic-sparkles">
  Create custom voices without training data. Just provide a voice ID and Inworld handles the rest.
</Card>

<Steps>
  <Step title="Enable Custom Voice">
    In your assistant configuration, select "Custom" voice option
  </Step>

  <Step title="Enter Voice ID">
    Provide your custom voice identifier in the Custom Voice ID field
  </Step>

  <Step title="Test & Refine">
    Test with sample text and adjust based on results
  </Step>
</Steps>

<Callout type="info">
  **Voice Cloning**: Contact Inworld support to set up custom voice cloning for your specific use case. Usually requires voice samples and setup time.
</Callout>

## Language Support & Quality

<Card title="🌍 Production-Ready Languages" icon="globe">
  Inworld provides native-quality voices for multiple languages with varying production readiness.
</Card>

| Language       | Status        | Voices Available | Quality Rating |
| -------------- | ------------- | ---------------- | -------------- |
| **English**    | 🟢 Production | 4+ voices        | ⭐⭐⭐⭐⭐          |
| **Spanish**    | 🟢 Production | 4+ voices        | ⭐⭐⭐⭐⭐          |
| **French**     | 🟢 Production | 4+ voices        | ⭐⭐⭐⭐           |
| **German**     | 🟡 Beta       | 2+ voices        | ⭐⭐⭐⭐           |
| **Chinese**    | 🟡 Beta       | 4+ voices        | ⭐⭐⭐⭐           |
| **Japanese**   | 🟡 Beta       | 2+ voices        | ⭐⭐⭐            |
| **Italian**    | 🟡 Beta       | 2+ voices        | ⭐⭐⭐            |
| **Portuguese** | 🟡 Beta       | 2+ voices        | ⭐⭐⭐            |
| **Dutch**      | 🟡 Beta       | 2+ voices        | ⭐⭐⭐            |
| **Korean**     | 🟡 Beta       | 2+ voices        | ⭐⭐⭐            |
| **Polish**     | 🟡 Beta       | 2+ voices        | ⭐⭐⭐            |

<Callout type="warning">
  **Beta Languages**: While functional, beta languages may have occasional quality variations. Test thoroughly before production use.
</Callout>

## API Integration

<CodeGroup>
  ```python Python theme={null}
  import requests
  import json

  def synthesize_with_emotions(text, voice_id="Ashley", language="en"):
      url = "https://api.inworld.ai/v1/text-to-speech/stream"
      
      headers = {
          "Authorization": "Bearer YOUR_INWORLD_API_KEY",
          "Content-Type": "application/json"
      }
      
      data = {
          "text": text,
          "voice_id": voice_id,
          "model": "inworld-tts-1",
          "language": language,
          "output_format": "wav",
          "sample_rate": 8000
      }
      
      response = requests.post(url, json=data, headers=headers, stream=True)
      return response

  # Example with emotional markup
  text_with_emotion = "[happy] Welcome to our service! [excited] How can I help you today?"
  response = synthesize_with_emotions(text_with_emotion, "Ashley", "en")
  ```

  ```javascript JavaScript theme={null}
  const synthesizeWithEmotions = async (text, voiceId = "Ashley", language = "en") => {
    const response = await fetch("https://api.inworld.ai/v1/text-to-speech/stream", {
      method: "POST",
      headers: {
        "Authorization": "Bearer YOUR_INWORLD_API_KEY",
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        text: text,
        voice_id: voiceId,
        model: "inworld-tts-1",
        language: language,
        output_format: "wav",
        sample_rate: 8000,
      }),
    });
    
    return response;
  };

  // Example with emotional markup
  const textWithEmotion = "[happy] Welcome to our service! [excited] How can I help you today?";
  const audioStream = await synthesizeWithEmotions(textWithEmotion, "Ashley", "en");
  ```

  ```curl cURL theme={null}
  curl -X POST "https://api.inworld.ai/v1/text-to-speech/stream" \
    -H "Authorization: Bearer YOUR_INWORLD_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "text": "[happy] Welcome to our service! [excited] How can I help you today?",
      "voice_id": "Ashley",
      "model": "inworld-tts-1",
      "language": "en",
      "output_format": "wav",
      "sample_rate": 8000
    }'
  ```
</CodeGroup>

## Use Case Examples

<Tabs>
  <Tab title="Customer Support">
    ```markdown theme={null}
    # Empathetic customer service
    [understanding] I completely understand your frustration. [reassuring] Let me help you resolve this issue right away. [confident] I'll have this sorted out for you in just a moment.
    ```

    **Best voices**: Ashley (EN), Lupita (ES), Hélène (FR)
    **Model**: `inworld-tts-1` for consistency
  </Tab>

  <Tab title="Gaming/Entertainment">
    ```markdown theme={null}
    # Character dialogue with personality
    [excited] A new challenger approaches! [confident] You think you can defeat me? [laughing] This should be entertaining! [determined] Let the battle begin!
    ```

    **Best voices**: Hades (commanding), Aria (heroic)
    **Model**: `inworld-tts-1.5-max` for maximum expression
  </Tab>

  <Tab title="Educational Content">
    ```markdown theme={null}
    # Engaging learning material
    [friendly] Today we're going to learn about photosynthesis. [curious] Have you ever wondered how plants make their own food? [explaining] It's actually a fascinating process!
    ```

    **Best voices**: Alex (EN), Mathieu (FR), Yichen (ZH)
    **Model**: `inworld-tts-1` for clarity
  </Tab>

  <Tab title="Multilingual Business">
    ```markdown theme={null}
    # Professional multilingual support
    English: [professional] Thank you for calling our support line.
    Spanish: [profesional] Gracias por llamar a nuestra línea de soporte.
    French: [professionnel] Merci d'avoir appelé notre ligne d'assistance.
    ```

    **Strategy**: Use native voices for each language
    **Model**: `inworld-tts-1` for business consistency
  </Tab>
</Tabs>

## Configuration Examples

<Card title="🎛️ Optimal Settings" icon="sliders">
  Recommended configurations for different use cases.
</Card>

<Accordion title="Phone Call Setup">
  ```json theme={null}
  {
    "model": "inworld-tts-1",
    "voice_id": "Ashley",
    "language": "en",
    "output_format": "wav",
    "sample_rate": 8000,
    "text": "[friendly] Thank you for calling! [helpful] How may I assist you today?"
  }
  ```

  **Features**:

  * Phone-compatible audio format
  * Friendly, professional tone
  * Emotional warmth in greeting
</Accordion>

<Accordion title="Multilingual Application">
  ```json theme={null}
  {
    "model": "inworld-tts-1",
    "voice_id": "Diego",
    "language": "es",
    "output_format": "wav",
    "sample_rate": 16000,
    "text": "[amigable] ¡Bienvenido! [servicial] ¿En qué puedo ayudarte hoy?"
  }
  ```

  **Features**:

  * Native Spanish voice
  * Cultural appropriate emotions
  * Higher quality audio format
</Accordion>

<Accordion title="Gaming/Interactive">
  ```json theme={null}
  {
    "model": "inworld-tts-1-max",
    "voice_id": "Hades",
    "language": "en",
    "output_format": "wav",
    "sample_rate": 24000,
    "text": "[menacing] You dare enter my domain? [angry] Prepare to face my wrath!"
  }
  ```

  **Features**:

  * Maximum expression model
  * Character-appropriate voice
  * High-quality audio for immersion
</Accordion>

## Best Practices

<Card title="🎯 Maximize Inworld's Emotional AI" icon="target">
  Get the most out of Inworld's unique features with these proven strategies.
</Card>

<Accordion title="Emotional Markup Guidelines">
  **Do's**:

  * Use emotions that match the content context
  * Place tags at natural speech boundaries
  * Mix emotions sparingly for realistic conversations
  * Test different voices with the same emotions

  **Don'ts**:

  * Overuse emotional tags (max 2-3 per sentence)
  * Use conflicting emotions close together
  * Rely only on markup - the text itself should convey meaning
  * Mix languages and emotions in complex ways
</Accordion>

<Accordion title="Voice Selection Strategy">
  **For Business Applications**:

  * English: Ashley, Alex, Aria
  * Spanish: Lupita, Rafael
  * French: Hélène, Mathieu

  **For Creative Content**:

  * Dramatic: Hades, Aria
  * Friendly: Ashley, Diego
  * Professional: Alex, Johanna

  **For Gaming**:

  * Heroes: Aria, Alex
  * Villains: Hades
  * NPCs: Ashley, Diego
</Accordion>

<Accordion title="Performance Optimization">
  ```python theme={null}
  # Efficient text processing
  def optimize_for_inworld(text):
      # Keep sentences under 50 words for best latency
      sentences = split_into_sentences(text)
      optimized = []
      
      for sentence in sentences:
          if len(sentence.split()) > 50:
              # Break long sentences at natural points
              optimized.extend(break_long_sentence(sentence))
          else:
              optimized.append(sentence)
      
      return optimized

  # Cache voice models for repeated use
  voice_cache = {}

  def get_cached_voice(voice_id, language):
      cache_key = f"{voice_id}_{language}"
      if cache_key not in voice_cache:
          voice_cache[cache_key] = load_voice_model(voice_id, language)
      return voice_cache[cache_key]
  ```
</Accordion>

## Pricing

<Card title="💰 Flexible Pricing Model" icon="dollar-sign">
  Pay-per-character with volume discounts and free tier for testing.
</Card>

| Plan             | Characters/Month | Price  | Features                     |
| ---------------- | ---------------- | ------ | ---------------------------- |
| **Free**         | 25,000           | \$0    | All voices, emotional markup |
| **Starter**      | 100,000          | \$9    | Priority processing          |
| **Professional** | 500,000          | \$29   | Custom voice support         |
| **Enterprise**   | Custom           | Custom | Dedicated support, SLA       |

<Callout type="info">
  **Cost Estimation**: Average phone call with emotions uses \~2,500 characters. A friendly greeting might be: "\[happy] Welcome to our service! \[helpful] How can I assist you today?" = \~85 characters
</Callout>

## Troubleshooting

<Accordion title="Emotional Markup Not Working">
  **Problem**: Emotions don't seem to affect the voice

  **Solutions**:

  * Verify emotion tag spelling (case-sensitive)
  * Check if the voice supports the specific emotion
  * Try with `inworld-tts-1.5-max` for stronger expression
  * Ensure tags are properly formatted: `[emotion]`
</Accordion>

<Accordion title="Language Detection Issues">
  **Problem**: Wrong language pronunciation

  **Solutions**:

  * Explicitly set language parameter in API call
  * Use native voices for each language
  * Avoid mixing languages in single requests
  * Verify voice ID supports the target language
</Accordion>

<Accordion title="Custom Voice Problems">
  **Problem**: Custom voice ID not working

  **Solutions**:

  * Verify custom voice ID with Inworld support
  * Check if voice is properly trained and available
  * Use fallback to standard voices during setup
  * Contact support for voice activation status
</Accordion>

## Migration Guide

<Tabs>
  <Tab title="From Other Providers">
    **Key Advantages of Switching**:

    * Emotional markup for better user engagement
    * Native multilingual support (11 languages)
    * Zero-shot voice cloning capabilities
    * AI-powered context awareness

    **Migration Steps**:

    1. Map existing voice preferences to Inworld voices
    2. Add emotional markup to enhance user experience
    3. Test multilingual capabilities if applicable
    4. Optimize for Inworld's strengths (emotions, languages)
  </Tab>

  <Tab title="Voice Mapping">
    **From ElevenLabs**:

    * Rachel → Ashley (professional female)
    * Antoni → Hades (authoritative male)
    * Bella → Ashley (friendly female)

    **From Deepgram**:

    * Asteria → Ashley (warm female)
    * Orion → Alex (professional male)
    * Luna → Ashley (gentle female)

    **Enhancement Opportunity**: Add emotional context to improve engagement
  </Tab>
</Tabs>

***

<Card title="🎭 Ready to Add Emotion to Your AI?" icon="rocket">
  Configure Inworld.ai in your [assistant settings](/ai-configuration) and start creating more engaging, expressive conversations!
</Card>