> Fetch clean Markdown by appending `.md` to any page URL under https://signalwire.com/docs or requesting it with the HTTP header `Accept: text/markdown`. The root index at https://signalwire.com/docs/llms.txt lists the available documentation indexes.

# OpenAI

> Learn how to use OpenAI TTS voices on the SignalWire platform.

OpenAI offers versatile multilingual voices balancing low latency and good quality.
While voices are optimized for English, they perform well across all
[supported languages][languages].

Consult
[OpenAI's Text-to-Speech documentation][tts]
for more information and audio samples for available voices.

## Models

OpenAI offers two TTS models with different quality and latency characteristics:

| Model      | Description                                         |
| ---------- | --------------------------------------------------- |
| `tts-1`    | **Default** - Standard quality, optimized for speed |
| `tts-1-hd` | High-definition quality, improved audio fidelity    |

## Voices

OpenAI provides 6 fully multilingual voices optimized for natural-sounding speech:

| Voice     | Description                |
| --------- | -------------------------- |
| `alloy`   | Neutral, balanced voice    |
| `echo`    | Warm, expressive voice     |
| `fable`   | British accent, articulate |
| `onyx`    | Deep, authoritative voice  |
| `nova`    | Energetic, friendly voice  |
| `shimmer` | Soft, gentle voice         |

## Languages

All OpenAI voices are fully multilingual and automatically adapt to the input text language.

Consult OpenAI's [supported languages resource][languages]
for an up-to-date list.

## Usage

OpenAI voice IDs conform to the following format:

```
openai.<voice>:<model>
```

**Parameters:**

* `voice` (required): One of: alloy, echo, fable, onyx, nova, shimmer
* `model` (optional): `tts-1` (default) or `tts-1-hd`

**Examples:**

```
openai.alloy
openai.nova:tts-1-hd
openai.fable:tts-1
```

---

## Examples

Learn how to use OpenAI voices on the SignalWire platform.

#### SWML

Use the
[**`languages`**](/docs/swml/reference/ai/languages#use-voice-strings)
SWML method to set one or more voices for an [AI agent](/docs/swml/reference/ai).

```yaml
version: 1.0.0
sections:
  main:
  - ai:
      prompt:
        text: Have an open-ended conversation about flowers.
      languages:
        - name: English
          code: en-US
          voice: openai.alloy
```

Alternatively, use the [**`say_voice`** parameter](/docs/swml/reference/play#variables)
of the [**`play`**](/docs/swml/reference/play)
SWML method to select a voice for basic TTS.

```yaml
version: 1.0.0
sections:
  main:
  - set:
      say_voice: "openai.alloy"
  - play: "say:Greetings. This is the Alloy voice from OpenAI's text-to-speech model."
```

#### Relay Realtime SDK

```javascript
// This example uses the Node.js SDK for SignalWire's Relay Realtime API.
const playback = await call.playTTS({ 
    text: "Greetings. This is the Alloy voice from OpenAI's text-to-speech model.",
    voice: "openai.alloy",
});
await playback.ended();
```

#### Call Flow Builder

OpenAI voices are not yet supported in Call Flow Builder.

[languages]: https://platform.openai.com/docs/guides/text-to-speech#supported-languages "OpenAI reference on supported languages."

[tts]: https://platform.openai.com/docs/guides/text-to-speech#supported-languages "OpenAI TTS documentation."

> Text-to-speech