> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zeroruntime.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gradium

> Python API reference for the gradium text-to-speech provider.

## GradiumTTS

Streaming text-to-speech with Gradium, using your own Gradium key. Low-latency
voices in English, French, German, Spanish and Portuguese, plus your own clones.

Authenticates with GRADIUM\_API\_KEY from your environment, or an explicit
`api_key`.

```python theme={null}
from zeroruntime.plugins import GradiumTTS  # direct to the vendor, with your key
```

### Fields

**model** `str` (default: UNSET)

TTS model: "default" (stable) or "gradium-tts-beta" to follow betas. Defaults to 'default'.

**voice\_id** `str` (default: UNSET)

Gradium voice ID, from the catalog or your own voices. Defaults to 'YTpq7expH9539ERJ'.

**temperature** `float | None` (default: UNSET)

Output variety from 0 to 1.4. Leave unset for Gradium's default (0.7). Defaults to None (not set).

**padding\_bonus** `float | None` (default: UNSET)

Speaking speed from -4 to 4. Negative is faster, positive slower. Leave unset for Gradium's default (0). Defaults to None (not set).

**rewrite\_rules** `str | None` (default: UNSET)

Text rewriting rules, e.g. "en", or "none" to disable them. Leave unset to use the voice's language. Defaults to None (not set).

**pronunciation\_id** `str | None` (default: UNSET)

Pronunciation dictionary to apply. Leave unset for none. Defaults to None (not set).

**base\_url** `str` (default: UNSET)

WebSocket endpoint of Gradium streaming text-to-speech. Change only for a proxy or a regional endpoint. Defaults to 'wss\://api.gradium.ai/api/speech/tts'.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.