LiveKit docs › Models › TTS › Additional models › Gradium

---

# Gradium TTS plugin guide

> How to use the Gradium TTS plugin for LiveKit Agents.

Available in:
- [ ] Node.js
- [x] Python

## Overview

This plugin allows you to use [Gradium](https://gradium.ai) as a TTS provider for your voice agents.

### Installation

Install the plugin from PyPI:

```shell
pip install "livekit-agents[gradium]~=1.5"

```

### Authentication

The Gradium plugin requires a [Gradium API key](https://eu.api.gradium.ai/studio).

Set `GRADIUM_API_KEY` in your `.env` file.

### Usage

Use Gradium TTS within an `AgentSession` or as a standalone speech generator. For example, you can use this TTS in the [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md).

```python
from livekit.plugins import gradium

session = AgentSession(
    tts=gradium.TTS(
    ),
    # ... llm, stt, etc.
)

```

### Parameters

This section describes some of the available parameters. See the [plugin reference](https://docs.livekit.io/reference/python/v1/livekit/plugins/gradium.md) for a complete list of all available parameters.

- **`voice_id`** _(string)_ (optional) - Default: `YTpq7expH9539ERJ`: Gradium TTS voice id to use.

- **`pronunciation_id`** _(string)_ (optional): ID of a Gradium pronunciation dictionary to apply when generating speech. To learn more, see [Pronunciation Dictionaries](https://docs.gradium.ai/guides/text-to-speech#pronunciation-dictionaries).

- **`json_config`** _(dict[str, Any])_ (optional): Defines advanced options for Gradium TTS such as speed, rewrite rules, and more. For available options, see the [Gradium API docs](https://gradium.ai/api_docs.html#tag/Documentation/Advanced-Options).

- **`model_name`** _(string)_ (optional) - Default: `default`: Gradium TTS model to use.

- **`model_endpoint`** _(string)_ (optional) - Default: `wss://eu.api.gradium.ai/api/speech/tts`: Sets the endpoint to be used, switch to `us.api.gradium.ai` for US region.

## Customizing pronunciation

Gradium TTS supports custom pronunciation through pronunciation dictionaries. Pass a dictionary ID to the `pronunciation_id` parameter to apply it to generated speech. To learn more, see [Pronunciation Dictionaries](https://docs.gradium.ai/guides/text-to-speech#pronunciation-dictionaries).

## Additional resources

The following resources provide more information about using Gradium with LiveKit Agents.

- **[Python package](https://pypi.org/project/livekit-plugins-gradium/)**: The `livekit-plugins-gradium` package on PyPI.

- **[Plugin reference](https://docs.livekit.io/reference/python/v1/livekit/plugins/gradium.md)**: Reference for the Gradium TTS plugin.

- **[Gradium docs](https://gradium.ai/api_docs.html)**: Gradium API documentation.

- **[Gradium STT](https://docs.livekit.io/agents/models/stt/gradium.md)**: Guide to the Gradium STT plugin with LiveKit Agents.

---

This document was rendered at 2026-06-07T11:35:26.726Z.
For the latest version of this document, see [https://docs.livekit.io/agents/models/tts/gradium.md](https://docs.livekit.io/agents/models/tts/gradium.md).

To explore all LiveKit documentation, see [llms.txt](https://docs.livekit.io/llms.txt).