> ## 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.

# Murf AI

> Use the Murf AI text-to-speech plugin in a Zero Runtime pipeline. Setup and usage in Python.

Murf AI is a **text-to-speech** plugin. It turns the LLM's reply into audio the caller
hears, using Murf AI's real-time `Falcon` model or studio-grade `Gen2` model across
150+ voices and 35+ languages.

## Setup

Set your Murf AI API key in the worker environment. Generate a key from the [Murf AI site](https://murf.ai/):

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

## Usage

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

```python Python theme={null}
from zrt.plugins import MurfAITTS

tts = MurfAITTS()

# Pipeline(tts=tts, ...)
```

## Parameters

| Parameter     | Type          | Default           | Description                                                                                        |
| ------------- | ------------- | ----------------- | -------------------------------------------------------------------------------------------------- |
| `api_key`     | `str \| None` | `None`            | Murf API key. Falls back to the `MURFAI_API_KEY` environment variable when unset.                  |
| `voice`       | `str`         | `"en-US-natalie"` | Murf `voiceId` (e.g. `"en-US-natalie"`) or the voice actor name (e.g. `"natalie"`).                |
| `model`       | `str`         | `"Falcon"`        | Synthesis model - `"Falcon"` (low-latency, real-time conversational) or `"Gen2"` (most realistic). |
| `sample_rate` | `int`         | `24000`           | Output audio sample rate, in Hz.                                                                   |

Spoken replies support interruptions. When the caller talks over the agent, the runtime
stops the audio and listens again. See the [plugin overview](/plugins/overview) for how TTS fits into the rest of the pipeline.