> ## 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.

# OpenAI TTS

> Configure OpenAI text-to-speech with tts-1, tts-1-hd, and gpt-4o-mini-tts models.

<Card title="OpenAI TTS" icon="comments">
  OpenAI TTS is supported in Burki through the `openai` TTS provider. Use it when you already use OpenAI keys or want GPT-4o mini TTS voice instructions.
</Card>

## Quick Setup

<Steps>
  <Step title="Get API Key">
    Create an OpenAI API key from the OpenAI dashboard.
  </Step>

  <Step title="Configure in Burki">
    Select `openai` as the TTS provider and add the API key at the assistant or organization level.
  </Step>

  <Step title="Choose Model and Voice">
    Pick a supported `model_id`, `voice_id`, and optional speed/instructions settings.
  </Step>
</Steps>

## Configuration

```json theme={null}
{
  "tts_settings": {
    "provider": "openai",
    "voice_id": "alloy",
    "model_id": "gpt-4o-mini-tts",
    "provider_config": {
      "speed": 1.0,
      "instructions": "Speak warmly and clearly, like a helpful support agent."
    }
  }
}
```

| Option         | Type   | Description                                                                |
| -------------- | ------ | -------------------------------------------------------------------------- |
| `provider`     | string | Use `openai`                                                               |
| `voice_id`     | string | OpenAI voice ID                                                            |
| `model_id`     | string | `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or pinned GPT-4o mini TTS snapshot |
| `speed`        | number | Speaking speed, clamped between `0.25` and `4.0`                           |
| `instructions` | string | Voice style instructions for `gpt-4o-mini-tts*` models                     |

## Supported Models

| Model ID                     | Notes                                                     |
| ---------------------------- | --------------------------------------------------------- |
| `tts-1`                      | Standard OpenAI TTS model optimized for speed             |
| `tts-1-hd`                   | Higher quality OpenAI TTS model                           |
| `gpt-4o-mini-tts`            | GPT-4o mini TTS model with instruction support            |
| `gpt-4o-mini-tts-2025-12-15` | Pinned GPT-4o mini TTS snapshot configured in the backend |

## Supported Voices

| Voice ID  | Description                |
| --------- | -------------------------- |
| `alloy`   | Balanced and clear         |
| `echo`    | Deep and resonant          |
| `fable`   | Warm and expressive        |
| `onyx`    | Strong and authoritative   |
| `nova`    | Bright and energetic       |
| `shimmer` | Soft and gentle            |
| `ash`     | Natural and conversational |
| `ballad`  | Melodic and expressive     |
| `coral`   | Warm and friendly          |
| `sage`    | Calm and wise              |
| `verse`   | Smooth and articulate      |
| `marin`   | Clear and professional     |
| `cedar`   | Warm and natural           |

## Runtime Behavior

* Burki requests PCM audio from OpenAI and converts it for the current telephony path.
* `gpt-4o-mini-tts*` models support the `instructions` field.
* HD telephony providers use linear16 at 16 kHz where supported; Twilio-style paths use µ-law at 8 kHz.
* Sentence buffering is used so the first audio chunk can start quickly without waiting for the entire LLM response.

## When to Use OpenAI TTS

* You want a simple provider stack with OpenAI for both LLM and TTS.
* You need model-level voice instructions.
* You prefer built-in voices over custom voice cloning.

For broader multilingual voice cloning, compare [ElevenLabs](/tts-providers/elevenlabs), [Cartesia](/tts-providers/cartesia), and [Inworld](/tts-providers/inworld).