> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.ortavox.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ortavox.ai/_mcp/server.

# Voice

> Configure the Text-to-Speech engine for your Ortavox Agent

The `voice` object defines how your Agent speaks. It is a **required** field when creating an Agent.

## Schema

```json
{
  "voice": {
    "provider": "elevenlabs",
    "voice_id": "dqzVFKHwZvR9YMQoFM67",
    "model": "eleven_turbo_v2_5"
  }
}
```

## Parameters

| Property   | Type     | Required | Description                                  |
| ---------- | -------- | -------- | -------------------------------------------- |
| `provider` | `string` | ✅        | TTS provider (see supported providers below) |
| `voice_id` | `string` | ✅        | Provider-specific voice identifier           |
| `model`    | `string` | ✅        | Provider-specific model name                 |

## Supported Providers

| Provider   | `provider` value | Notes                                          |
| ---------- | ---------------- | ---------------------------------------------- |
| ElevenLabs | `elevenlabs`     | Recommended — highest expressiveness           |
| OpenAI     | `openai`         | Fast and reliable (Alloy, Nova, Shimmer, etc.) |
| Google     | `google`         | Multi-language support                         |
| Cartesia   | `cartesia`       | Ultra-low latency                              |