# Text to speech

> POST /v1/audio/speech: Gemini text-to-speech through OpenAI's speech API, with 30 voices, styles in plain words, MP3, WAV or PCM, and prices.

Source: https://zurelay.com/docs/speech

Turn text into natural speech with Gemini’s text-to-speech models, through OpenAI’s speech API: 30 voices, a style you describe in plain words, and MP3, WAV or PCM back in a few seconds.

`POST /v1/audio/speech`

| Model | ID | Text in, per 1M tokens | Audio out, per 1M tokens | Audio tokens a second | About a minute |
| --- | --- | --- | --- | --- | --- |
| [Gemini 3.1 Flash TTS](https://zurelay.com/models/gemini-3.1-flash-tts) | `gemini-3.1-flash-tts` | $0.60 | $12.00 | 32 | $0.023 |
| [Gemini 2.5 Pro TTS](https://zurelay.com/models/gemini-2.5-pro-tts) | `gemini-2.5-pro-tts` | $0.60 | $12.00 | 25 | $0.018 |
| [Gemini 2.5 Flash TTS](https://zurelay.com/models/gemini-2.5-flash-tts) | `gemini-2.5-flash-tts` | $0.30 | $6.00 | 25 | $0.009 |

## Make speech

**Python** (`speak.py`):

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY")

speech = client.audio.speech.create(
    model="gemini-3.1-flash-tts",
    voice="Kore",
    input="Your order has shipped and arrives on Friday.",
    instructions="Say it warmly, at a relaxed pace",
)
speech.write_to_file("shipped.mp3")
```

**Node.js** (`speak.mjs`):

```javascript
import OpenAI from "openai";
import { writeFile } from "node:fs/promises";

const client = new OpenAI({ baseURL: "https://api.zurelay.com/v1", apiKey: process.env.ZURELAY_API_KEY });

const speech = await client.audio.speech.create({
  model: "gemini-3.1-flash-tts",
  voice: "Kore",
  input: "Your order has shipped and arrives on Friday.",
  instructions: "Say it warmly, at a relaxed pace",
});
await writeFile("shipped.mp3", Buffer.from(await speech.arrayBuffer()));
```

**cURL**:

```bash
curl https://api.zurelay.com/v1/audio/speech \
  -H "Authorization: Bearer $ZURELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-tts",
    "voice": "Kore",
    "input": "Your order has shipped and arrives on Friday.",
    "response_format": "wav"
  }' -o shipped.wav
```

Any OpenAI SDK works: point it at `https://api.zurelay.com/v1` and call its speech method. The reply is the audio file itself.

## Parameters

- `model` (string, required): A speech model ID from the table.
- `input` (string, required): The text to speak, up to 5,000 characters. Split longer text into several requests.
- `voice` (string): One of the 30 voices below, or an OpenAI voice name such as `alloy` or `nova`. Default `Kore`.
- `instructions` (string): How to say it, in plain words: `Say cheerfully`, `Whisper, like a secret`, `Read slowly, like a bedtime story`. Up to 2,000 characters.
- `response_format` (string): `mp3` (the default), `wav`, or `pcm`: raw 24 kHz, 16-bit, mono samples.
- `speed` (number): Not supported: ask for the pace in `instructions` instead. Only `1` is accepted.
- `models` (array): Smart routing for this request: other speech models to try, in order, if the model is down. See [Smart routing](https://zurelay.com/docs/smart-routing).

> **Tip:** The audio comes back when all of it is made. Measured at full length (5,000 characters): the Flash models take about a minute, and Gemini 2.5 Pro TTS about five and a half. Give your HTTP client a timeout of 10 minutes (the OpenAI SDKs’ default), or send long text in parts.

## Voices

| Voice | Sounds | Voice | Sounds |
| --- | --- | --- | --- |
| `Zephyr` | Bright | `Puck` | Upbeat |
| `Charon` | Informative | `Kore` | Firm |
| `Fenrir` | Excitable | `Leda` | Youthful |
| `Orus` | Firm | `Aoede` | Breezy |
| `Callirrhoe` | Easy-going | `Autonoe` | Bright |
| `Enceladus` | Breathy | `Iapetus` | Clear |
| `Umbriel` | Easy-going | `Algieba` | Smooth |
| `Despina` | Smooth | `Erinome` | Clear |
| `Algenib` | Gravelly | `Rasalgethi` | Informative |
| `Laomedeia` | Upbeat | `Achernar` | Soft |
| `Alnilam` | Firm | `Schedar` | Even |
| `Gacrux` | Mature | `Pulcherrima` | Forward |
| `Achird` | Friendly | `Zubenelgenubi` | Casual |
| `Vindemiatrix` | Gentle | `Sadachbia` | Lively |
| `Sadaltager` | Knowledgeable | `Sulafat` | Warm |

Code written for OpenAI keeps working: its voice names map to a Gemini voice of a similar character.

| OpenAI voice | Speaks as |
| --- | --- |
| `alloy` | Kore |
| `ash` | Charon |
| `ballad` | Algieba |
| `coral` | Aoede |
| `echo` | Puck |
| `fable` | Fenrir |
| `nova` | Leda |
| `onyx` | Orus |
| `sage` | Zephyr |
| `shimmer` | Callirrhoe |
| `verse` | Umbriel |
| `marin` | Despina |
| `cedar` | Iapetus |

## Style and pacing

- Describe the delivery the way you’d brief a voice actor: mood, pace, volume, accent.
- Keep the direction in `instructions` and only the words to say in `input`, so the direction isn’t read out.
- The language is picked up from the text, so a Spanish sentence is spoken in Spanish.

## Paying for speech

Speech is billed on tokens: the text you send at the input price, and the audio you get back at the output price. Each second of audio is a set number of tokens, which the table lists for each model, so its last column is what a minute costs. Each reply says what it was billed on in its `x-zurelay-input-tokens` and `x-zurelay-output-tokens` headers, and every request is in your request log. Requests that fail cost nothing. With [smart routing](https://zurelay.com/docs/smart-routing) on, another speech model may answer when the one you asked for is down: `x-zurelay-model` names it, and it’s billed at its price.

> **Tip:** Speech isn’t stored: save the file you get back. The same text and voice give a slightly different reading each time.

Try voices and styles in the dashboard’s [Playground](https://zurelay.com/app/playground).