> ## 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.

# Text-to-Speech Providers

> Choose the perfect voice for your AI assistant from our comprehensive TTS provider ecosystem

<Card title="🎙️ Give Your Assistant a Voice" icon="microphone">
  Transform text into natural, human-like speech with our integrated TTS providers. Each provider offers unique advantages for different use cases.
</Card>

## Quick Provider Comparison

<CardGroup cols={2}>
  <Card title="⚡ ElevenLabs" icon="wand-magic-sparkles" href="/tts-providers/elevenlabs">
    **Premium Quality & Customization**

    70+ languages, voice cloning, advanced controls

    *Best for: High-quality customer interactions*
  </Card>

  <Card title="🚀 Deepgram Aura" icon="bolt" href="/tts-providers/deepgram">
    **Ultra-Low Latency**

    3x faster than competitors, phone-optimized

    *Best for: Real-time conversations*
  </Card>

  <Card title="🎯 Cartesia Sonic 3" icon="bullseye" href="/tts-providers/cartesia">
    **Multilingual Excellence**

    42 languages, voice cloning, low latency

    *Best for: Multilingual agents, global deployments*
  </Card>

  <Card title="☁️ Azure Speech" icon="cloud" href="/tts-providers/azure">
    **Enterprise Scale**

    500+ neural voices, 100+ languages

    *Best for: Enterprise, Azure ecosystem*
  </Card>

  <Card title="🎭 Inworld.ai" icon="masks-theater" href="/tts-providers/inworld">
    **AI-Powered Emotions**

    Multilingual, emotional markup, voice cloning

    *Best for: Expressive, contextual responses*
  </Card>

  <Card title="🎙️ Resemble AI" icon="microphone" href="/tts-providers/resemble">
    **Custom Voice Creation**

    WebSocket streaming, personalized voices

    *Best for: Brand-specific voice identity*
  </Card>

  <Card title="🧠 OpenAI TTS" icon="comments" href="/tts-providers/openai">
    **Instruction-Aware Voices**

    `tts-1`, `tts-1-hd`, and `gpt-4o-mini-tts`

    *Best for: OpenAI-native stacks and voice instructions*
  </Card>

  <Card title="🧩 Additional Providers" icon="puzzle-piece" href="#additional-supported-providers">
    **Kokoro, Uplift, Murf, Soniox**

    Self-hosted and specialized provider options

    *Best for: Custom deployments and specialized voices*
  </Card>
</CardGroup>

## Feature Matrix

| Provider       | Latency                          | Languages       | Voice Cloning | Streaming         | Best For                      |
| -------------- | -------------------------------- | --------------- | ------------- | ----------------- | ----------------------------- |
| **ElevenLabs** | Vendor-reported low latency      | 70+             | ✅ Advanced    | WebSocket         | Premium quality               |
| **Deepgram**   | Vendor-reported very low latency | English         | ❌             | WebSocket         | Speed & phone calls           |
| **Cartesia**   | Vendor-reported low latency      | 42              | ✅ Yes         | WebSocket         | Multilingual                  |
| **Azure**      | Provider/config dependent        | 100+            | ❌             | HTTP              | Microsoft ecosystem           |
| **Inworld**    | Provider/config dependent        | 11              | ✅ Zero-shot   | HTTP/WS           | Emotional expression          |
| **Resemble**   | Provider/config dependent        | English         | ✅ Custom      | WebSocket         | Brand voices                  |
| **OpenAI**     | Provider/config dependent        | English-first   | ❌             | HTTP streaming    | OpenAI-native stacks          |
| **Kokoro**     | Self-hosted dependent            | Model-dependent | ❌             | HTTP              | Self-hosted/local deployments |
| **Uplift**     | Provider-dependent               | Specialized     | ❌             | Streaming service | Uplift voices                 |
| **Murf**       | Provider-dependent               | Multi-language  | ❌             | HTTP              | Style/rate/pitch controls     |
| **Soniox**     | Provider-dependent               | Model-dependent | ❌             | Streaming service | Soniox voice stack            |

<Callout type="info">
  **New to TTS?** Start with **ElevenLabs** for the best balance of quality and features, **Deepgram** if speed is your priority, or **Cartesia** for multilingual support.
</Callout>

## Setup Overview

All providers follow the same basic setup pattern:

<Steps>
  <Step title="Get API Credentials">
    Sign up with your chosen provider and obtain API keys
  </Step>

  <Step title="Configure in Burki">
    Add your credentials in the assistant's AI Configuration → TTS tab
  </Step>

  <Step title="Select Voice & Model">
    Choose from available voices and models for your use case
  </Step>

  <Step title="Fine-tune Settings">
    Adjust speed, stability, and other provider-specific options
  </Step>
</Steps>

## Provider Deep Dives

<CardGroup cols={1}>
  <Card title="🎭 ElevenLabs - Premium Voice Quality" href="/tts-providers/elevenlabs">
    **Latest Models**: Flash v2.5 (75ms), v3 (70+ languages), Turbo v2.5

    **Key Features**: Advanced voice controls, multilingual support, custom voice creation

    **Perfect For**: Customer service, content creation, multilingual applications

    → [Complete ElevenLabs Guide](/tts-providers/elevenlabs)
  </Card>

  <Card title="⚡ Deepgram Aura - Ultra-Fast TTS" href="/tts-providers/deepgram">
    **Latest Models**: Aura-2 (next-gen), Aura (proven)

    **Key Features**: Industry-leading speed, phone optimization, µ-law encoding

    **Perfect For**: Real-time phone calls, live chat, interactive applications

    → [Complete Deepgram Guide](/tts-providers/deepgram)
  </Card>

  <Card title="🎯 Cartesia Sonic 3 - Multilingual Excellence" href="/tts-providers/cartesia">
    **Latest Models**: sonic-3 (latest), sonic-3-2025-10-27 (stable)

    **Key Features**: 42 languages, voice cloning from \~5 sec, low latency WebSocket

    **Perfect For**: Global deployments, multilingual voice agents

    → [Complete Cartesia Guide](/tts-providers/cartesia)
  </Card>

  <Card title="☁️ Azure Speech - Enterprise Scale" href="/tts-providers/azure">
    **Latest Models**: Neural (high-quality), Standard (basic)

    **Key Features**: 500+ voices, 100+ languages, SSML support, Microsoft integration

    **Perfect For**: Enterprise applications, Azure ecosystem users

    → [Complete Azure Guide](/tts-providers/azure)
  </Card>

  <Card title="🎪 Inworld.ai - AI-Powered Expression" href="/tts-providers/inworld">
    **Latest Models**: `inworld-tts-1`, `inworld-tts-1-max`, `inworld-tts-1.5-max`, `inworld-tts-1.5-mini`

    **Key Features**: Emotional markup, context awareness, 11 languages

    **Perfect For**: Gaming, entertainment, emotional customer support

    → [Complete Inworld Guide](/tts-providers/inworld)
  </Card>

  <Card title="🎙️ Resemble AI - Custom Brand Voices" href="/tts-providers/resemble">
    **Key Features**: WebSocket streaming, unlimited voice creation, business plans

    **Perfect For**: Brand consistency, personalized experiences, enterprise

    → [Complete Resemble Guide](/tts-providers/resemble)
  </Card>

  <Card title="🧠 OpenAI TTS - Instruction-Aware Speech" href="/tts-providers/openai">
    **Latest Models**: `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`

    **Key Features**: Built-in OpenAI voices, speed control, instruction support on GPT-4o mini TTS models

    **Perfect For**: Teams already using OpenAI keys and model-specific voice instructions

    → [Complete OpenAI TTS Guide](/tts-providers/openai)
  </Card>
</CardGroup>

## Additional Supported Providers

The backend also supports these TTS providers through `tts_settings.provider`:

| Provider | Provider Key | Important Options                                                                                                      |
| -------- | ------------ | ---------------------------------------------------------------------------------------------------------------------- |
| Kokoro   | `kokoro`     | `voice_id`, `model_id`, `language`, `speed`, `kokoro_base_url`; no API key required by default                         |
| Uplift   | `uplift`     | `voice_id`, `model_id`, `language`, `output_format`                                                                    |
| Murf     | `murf`       | `voice_id`, `model_id`, `style`, `rate`, `pitch`, `region`, optional `variation`, `locale`, `pronunciation_dictionary` |
| Soniox   | `soniox`     | `voice_id`, `model_id`, `language`                                                                                     |

```json theme={null}
{
  "tts_settings": {
    "provider": "kokoro",
    "voice_id": "af_heart",
    "model_id": "kokoro",
    "language": "en",
    "provider_config": {
      "kokoro_base_url": "http://localhost:8880"
    }
  }
}
```

<Callout type="warning">
  AWS Polly and Google TTS appear only as future placeholders in backend enum comments and are not registered in the active TTS factory. Do not document them as supported providers until they are wired.
</Callout>

## Advanced Topics

<CardGroup cols={3}>
  <Card title="🎛️ Voice Tuning" icon="sliders" href="/tts-providers/voice-tuning">
    Master stability, similarity, and style controls across all providers
  </Card>

  <Card title="🔧 Troubleshooting" icon="wrench" href="/tts-providers/troubleshooting">
    Common issues and solutions with step-by-step fixes
  </Card>

  <Card title="📈 Best Practices" icon="chart-line" href="/tts-providers/best-practices">
    Performance optimization, cost reduction, and production tips
  </Card>
</CardGroup>

## Related Documentation

<Card title="🔗 See Also" icon="link">
  **Configuration**: Learn how to configure TTS in your [AI Configuration](/ai-configuration) settings.

  **Integration**: Understand how TTS fits into the overall [Architecture](/architecture) of Burki Voice AI.

  **Call Management**: Discover how TTS works with [Call Management](/call-management) features.
</Card>

## Quick Start Guide

<Tabs>
  <Tab title="Business Calls">
    **Recommended Setup:**

    * **Provider**: ElevenLabs or Deepgram
    * **Model**: Flash v2.5 or Aura-2
    * **Voice**: Professional (Rachel, Asteria)
    * **Settings**: Stability 0.5, Speaker Boost ON
  </Tab>

  <Tab title="Customer Support">
    **Recommended Setup:**

    * **Provider**: ElevenLabs
    * **Model**: Turbo v2.5
    * **Voice**: Warm & friendly (Bella, Luna)
    * **Settings**: Stability 0.6, Similarity 0.75
  </Tab>

  <Tab title="Multilingual">
    **Recommended Setup:**

    * **Provider**: Cartesia Sonic 3
    * **Model**: sonic-3
    * **Voice**: Katie (female) or Kiefer (male)
    * **Settings**: Language-specific code (42 languages)
  </Tab>

  <Tab title="Enterprise">
    **Recommended Setup:**

    * **Provider**: Azure Speech
    * **Model**: Neural
    * **Voice**: Jenny (en-US) or region-specific
    * **Settings**: SSML for fine control, closest Azure region
  </Tab>

  <Tab title="Real-time Apps">
    **Recommended Setup:**

    * **Provider**: Deepgram
    * **Model**: Aura-2
    * **Voice**: Fast response (Asteria, Thalia)
    * **Settings**: Latency 1, µ-law encoding
  </Tab>
</Tabs>

<Callout type="warning">
  **API Rate Limits**: Each provider has different rate limits and pricing models. Check the individual provider pages for detailed pricing information.
</Callout>

***

<Card title="🚀 Ready to Get Started?" icon="rocket">
  Choose your provider and dive into the detailed setup guides, or check out our [Best Practices](/tts-providers/best-practices) for optimization tips.
</Card>