> ## 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.

# Cartesia

> Use the Cartesia text-to-speech plugin in a Zero Runtime pipeline. Setup and usage in Python, JavaScript, and Go.

Cartesia is a **text-to-speech** plugin. It turns the LLM's reply into audio the caller
hears.

## Setup

Set your Cartesia API key in the worker environment. Generate a key from the [Cartesia dashboard](https://play.cartesia.ai/keys):

```bash theme={null}
export CARTESIA_API_KEY=<key>
```

## Usage

Import the plugin and pass it to the pipeline's `tts` slot.

<CodeGroup>
  ```python Python theme={null}
  from zrt.plugins import CartesiaTTS

  tts = CartesiaTTS()

  # Pipeline(tts=tts, ...)
  ```
</CodeGroup>

## Parameters

*Constructor parameters for the Python SDK (`CartesiaTTS`). The JavaScript and Go SDKs expose equivalent options where supported, in their idiomatic form (camelCase / `TTSOptions` struct).*

| Parameter                | Type                 | Default                                  | Description                                                                             |
| ------------------------ | -------------------- | ---------------------------------------- | --------------------------------------------------------------------------------------- |
| `api_key`                | `str`                | `None`                                   | Cartesia API key. Falls back to the `CARTESIA_API_KEY` environment variable when unset. |
| `model`                  | `str`                | `"sonic-2"`                              | Cartesia voice model.                                                                   |
| `voice_id`               | `str \| list[float]` | `"f8f5f1b2-f02d-4d8e-a40d-fd850a487b3d"` | Voice to speak with: a voice ID or an embedding vector.                                 |
| `language`               | `str`                | `"en"`                                   | Language of the spoken output.                                                          |
| `generation_config`      | `GenerationConfig`   | `None`                                   | Fine-grained synthesis settings such as speed and emotion.                              |
| `pronunciation_dict_id`  | `str`                | `None`                                   | ID of a custom pronunciation dictionary to apply.                                       |
| `max_buffer_delay_ms`    | `int`                | `None`                                   | Maximum time to buffer text before synthesizing, trading latency for smoother audio.    |
| `enable_word_timestamps` | `bool`               | `False`                                  | Return per-word timing alongside the audio.                                             |

## Import paths

| SDK        | Import                                | Constructor                              |
| ---------- | ------------------------------------- | ---------------------------------------- |
| Python     | `from zrt.plugins import CartesiaTTS` | `CartesiaTTS()`                          |
| JavaScript | `from '@zrt/js-sdk/plugins/cartesia'` | `CartesiaTTS()`                          |
| Go         | `.../zrt-golang-sdk/plugins/cartesia` | `cartesia.NewTTS(cartesia.TTSOptions{})` |

Spoken replies support interruptions. When the caller talks over the agent, the runtime
stops the audio and listens again.