> ## 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.

# Azure Speech TTS

> Azure text-to-speech with neural voices, broad language support, and Microsoft ecosystem integration

<Card title="☁️ Azure Speech: Enterprise Scale" icon="cloud">
  Microsoft's neural TTS service with broad voice and language support. Seamless integration with Azure ecosystem and SSML support. Good for organizations already using Microsoft services.
</Card>

## Quick Setup

<Steps>
  <Step title="Create Azure Speech Resource">
    1. Follow the [Azure AI Speech resource quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-text-to-speech)
    2. Create a new **Speech** resource
    3. Select your subscription, resource group, and region
    4. Note your **Key** and **Region** from the resource's Keys and Endpoint page
  </Step>

  <Step title="Configure in Burki">
    1. Go to **AI Configuration** → **TTS** tab
    2. Select **Azure Speech** as provider
    3. Enter your **API Key** and **Region** (e.g., `eastus`, `westus2`)
  </Step>

  <Step title="Choose Voice & Model">
    Select your preferred neural voice from the dropdown
  </Step>
</Steps>

<Callout type="info">
  **Free Tier**: Azure offers 500,000 characters per month free. Neural voices are available on all tiers.
</Callout>

## Available Models

<CardGroup cols={2}>
  <Card title="🧠 Neural" icon="brain">
    **High-Quality Neural Voices**

    Natural intonation and human-like speech

    **Quality**: Premium
    **Best for**: All production applications
  </Card>

  <Card title="📢 Standard" icon="volume-high">
    **Standard TTS Voices**

    Basic text-to-speech synthesis

    **Quality**: Good
    **Best for**: Legacy compatibility
  </Card>
</CardGroup>

<Callout type="tip">
  **Recommendation**: Always use **Neural** voices for the best quality. Standard voices are legacy and should only be used for specific compatibility needs.
</Callout>

## Available Voices

### English Voices

<Accordion title="American English (en-US)">
  <CardGroup cols={3}>
    <Card title="Jenny" icon="user">
      **Clear & Professional**

      Perfect for business applications

      `Voice ID: en-US-JennyNeural`
    </Card>

    <Card title="Aria" icon="user">
      **Warm & Natural**

      Great for friendly interactions

      `Voice ID: en-US-AriaNeural`
    </Card>

    <Card title="Guy" icon="user">
      **Natural & Confident**

      Strong, authoritative voice

      `Voice ID: en-US-GuyNeural`
    </Card>

    <Card title="Davis" icon="user">
      **Friendly & Approachable**

      Ideal for customer service

      `Voice ID: en-US-DavisNeural`
    </Card>

    <Card title="Jane" icon="user">
      **Professional**

      Clear business voice

      `Voice ID: en-US-JaneNeural`
    </Card>

    <Card title="Jason" icon="user">
      **Clear**

      Reliable male voice

      `Voice ID: en-US-JasonNeural`
    </Card>
  </CardGroup>
</Accordion>

<Accordion title="British English (en-GB)">
  <CardGroup cols={2}>
    <Card title="Sonia" icon="user">
      **Clear & Professional**

      British female voice

      `Voice ID: en-GB-SoniaNeural`
    </Card>

    <Card title="Ryan" icon="user">
      **Warm**

      British male voice

      `Voice ID: en-GB-RyanNeural`
    </Card>
  </CardGroup>
</Accordion>

### Other Languages

<Accordion title="Spanish (es-ES)">
  <CardGroup cols={2}>
    <Card title="Elvira" icon="user">
      **Natural**

      Spanish female voice

      `Voice ID: es-ES-ElviraNeural`
    </Card>

    <Card title="Alvaro" icon="user">
      **Clear**

      Spanish male voice

      `Voice ID: es-ES-AlvaroNeural`
    </Card>
  </CardGroup>
</Accordion>

<Accordion title="French (fr-FR)">
  <CardGroup cols={2}>
    <Card title="Denise" icon="user">
      **Natural**

      French female voice

      `Voice ID: fr-FR-DeniseNeural`
    </Card>

    <Card title="Henri" icon="user">
      **Clear**

      French male voice

      `Voice ID: fr-FR-HenriNeural`
    </Card>
  </CardGroup>
</Accordion>

<Accordion title="Arabic (ar-SA)">
  <CardGroup cols={2}>
    <Card title="Salma" icon="user">
      **Natural**

      Arabic female voice

      `Voice ID: ar-SA-SalmaNeural`
    </Card>

    <Card title="Hamed" icon="user">
      **Clear**

      Arabic male voice

      `Voice ID: ar-SA-HamedNeural`
    </Card>
  </CardGroup>
</Accordion>

<Accordion title="All Configured Voices">
  | Voice      | Language | Gender | Voice ID             | Description               |
  | ---------- | -------- | ------ | -------------------- | ------------------------- |
  | **Jenny**  | en-US    | Female | `en-US-JennyNeural`  | Clear and professional    |
  | **Aria**   | en-US    | Female | `en-US-AriaNeural`   | Warm and natural          |
  | **Guy**    | en-US    | Male   | `en-US-GuyNeural`    | Natural and confident     |
  | **Davis**  | en-US    | Male   | `en-US-DavisNeural`  | Friendly and approachable |
  | **Jane**   | en-US    | Female | `en-US-JaneNeural`   | Professional              |
  | **Jason**  | en-US    | Male   | `en-US-JasonNeural`  | Clear                     |
  | **Sonia**  | en-GB    | Female | `en-GB-SoniaNeural`  | Clear and professional    |
  | **Ryan**   | en-GB    | Male   | `en-GB-RyanNeural`   | Warm                      |
  | **Elvira** | es-ES    | Female | `es-ES-ElviraNeural` | Natural                   |
  | **Alvaro** | es-ES    | Male   | `es-ES-AlvaroNeural` | Clear                     |
  | **Denise** | fr-FR    | Female | `fr-FR-DeniseNeural` | Natural                   |
  | **Henri**  | fr-FR    | Male   | `fr-FR-HenriNeural`  | Clear                     |
  | **Salma**  | ar-SA    | Female | `ar-SA-SalmaNeural`  | Natural                   |
  | **Hamed**  | ar-SA    | Male   | `ar-SA-HamedNeural`  | Clear                     |
</Accordion>

<Callout type="info">
  **500+ More Voices**: Azure offers hundreds of additional voices. Visit the [Azure Voice Gallery](https://speech.microsoft.com/portal/voicegallery) for the complete list.
</Callout>

## Voice Controls

Azure Speech provides advanced voice customization through SSML:

<Tabs>
  <Tab title="Speaking Rate">
    **Controls speech speed** (Range: 0.5 - 2.0)

    * **0.5**: Half speed (very slow)
    * **1.0**: ✅ **Normal speed (Recommended)**
    * **2.0**: Double speed (very fast)

    ```xml theme={null}
    <prosody rate="+20%">
      Speaking slightly faster than normal.
    </prosody>
    ```
  </Tab>

  <Tab title="Pitch">
    **Controls voice pitch** (Range: 0.5 - 2.0)

    * **0.5**: Very low pitch
    * **1.0**: ✅ **Normal pitch (Recommended)**
    * **2.0**: Very high pitch

    ```xml theme={null}
    <prosody pitch="+10%">
      Speaking with slightly higher pitch.
    </prosody>
    ```
  </Tab>

  <Tab title="SSML Support">
    **Full SSML markup for advanced control**

    ```xml theme={null}
    <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US">
      <voice name="en-US-JennyNeural">
        <prosody rate="+10%" pitch="+5%">
          Hello! How can I help you today?
        </prosody>
      </voice>
    </speak>
    ```
  </Tab>
</Tabs>

## Configuration Options

### Audio Format

Azure Speech automatically outputs the appropriate format for your telephony provider:

* **Twilio/Telnyx**: PCM μ-law @ 8kHz (`Raw8Khz8BitMonoMULaw`)
* **Vonage**: PCM 16-bit @ 16kHz (`Raw16Khz16BitMonoPcm`)

## Configuration in Burki

To use Azure Speech TTS in your assistant:

<Steps>
  <Step title="Get Azure Credentials">
    Create a Speech resource using the [Azure AI Speech resource quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-text-to-speech) and copy your **Subscription Key** and **Region**.
  </Step>

  <Step title="Add to Burki">
    Go to **Settings** → **Provider Keys** → **TTS** and add your Azure Speech credentials.
  </Step>

  <Step title="Configure Assistant">
    Edit your assistant, select **Azure Speech** as the TTS provider, and choose a voice.
  </Step>
</Steps>

### SSML Support

Azure Speech supports SSML for advanced voice control:

```xml theme={null}
<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US">
    <voice name="en-US-JennyNeural">
        <prosody rate="+10%" pitch="+5%">
            Welcome to our service!
        </prosody>
        <break time="500ms"/>
        How can I assist you today?
    </voice>
</speak>
```

Use SSML tags in your assistant's responses for fine-grained control over pronunciation, emphasis, and pacing.

## Regional Selection

<Callout type="tip">
  **Latency Optimization**: Choose the Azure region closest to your deployment for optimal latency.
</Callout>

| Region          | Location       | Best For             |
| --------------- | -------------- | -------------------- |
| `eastus`        | East US        | North America (East) |
| `westus2`       | West US 2      | North America (West) |
| `westeurope`    | Netherlands    | Europe               |
| `southeastasia` | Singapore      | Asia-Pacific         |
| `australiaeast` | Australia East | Australia/Oceania    |

## Pricing Overview

| Tier         | Characters/Month | Neural Voices | Price             |
| ------------ | ---------------- | ------------- | ----------------- |
| **Free**     | 500,000          | Yes           | \$0               |
| **Standard** | Pay-as-you-go    | Yes           | \$16 per 1M chars |

<Callout type="info">
  **Enterprise**: Contact Azure for custom pricing on high-volume usage and reserved capacity.
</Callout>

## Common Issues & Solutions

<Accordion title="Authentication Failed">
  **Problem**: API returns 401 Unauthorized

  **Solutions**:

  * Verify your Azure Speech Key is correct in **Settings** → **Provider Keys**
  * Ensure the key is from your Speech resource (not another Azure service)
  * Check that the region matches your Speech resource's region
</Accordion>

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

  **Solutions**:

  * Verify the voice ID format (e.g., `en-US-JennyNeural`)
  * Check that the voice is available in your region
  * Ensure your subscription tier supports the selected voice
</Accordion>

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

  **Solutions**:

  * Select an Azure region closer to your users
  * Burki uses streaming synthesis for optimal performance
  * Consider caching common phrases
</Accordion>

## Best Practices

<Cards>
  <Card title="🌍 Regional Selection" icon="globe">
    Deploy in the Azure region closest to your users for minimal latency
  </Card>

  <Card title="🔧 SSML for Control" icon="sliders">
    Use SSML markup for precise control over pronunciation, pauses, and emphasis
  </Card>

  <Card title="🎯 Voice Consistency" icon="check">
    Stick to one voice per assistant for a consistent user experience
  </Card>

  <Card title="💰 Cost Monitoring" icon="chart-line">
    Monitor usage in Azure Portal to stay within budget
  </Card>
</Cards>

## See Also

<CardGroup cols={3}>
  <Card title="🎯 Multilingual?" href="/tts-providers/cartesia">
    **Cartesia Sonic 3** - 42 languages with voice cloning
  </Card>

  <Card title="⚡ Need Speed?" href="/tts-providers/deepgram">
    **Deepgram Aura** - speed-focused realtime TTS
  </Card>
</CardGroup>

<Card title="🔗 Additional Resources" icon="link">
  **Azure Speech setup**: [Azure AI Speech text-to-speech quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-text-to-speech)

  **Voice Gallery**: [Azure Voice Gallery](https://speech.microsoft.com/portal/voicegallery)

  **Documentation**: [Azure Speech Service Docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/)

  **Pricing**: [Azure Speech Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/)
</Card>

***

<Card title="🚀 Ready to Use Azure Speech?" icon="rocket">
  Head back to your [assistant configuration](/ai-configuration) and set up Azure Speech for managed TTS.
</Card>