> ## 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.

# Groq

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

Groq is a **text-to-speech** plugin. It synthesizes the LLM's reply into natural-sounding
speech via Groq's low-latency inference API.

## Setup

Set your Groq API key in the worker environment. Generate a key from the [Groq console](https://console.groq.com/keys):

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

## Usage

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

<CodeGroup>
  ```python Python theme={null}
  from zeroruntime.plugins import GroqTTS

  tts = GroqTTS()

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

  ```typescript Node JS theme={null}
  import { GroqTTS } from '@zeroruntime/js-sdk/plugins';

  const tts = GroqTTS();

  // Pipeline({ tts, ... })
  ```
</CodeGroup>

## Parameters

| Parameter | Type | Default | Description |
| - | - | - | - |
| `api_key` | `str \| None` | `None` | Groq API key. Falls back to the `GROQ_API_KEY` environment variable when unset. |
| `model` | `str` | `"playai-tts"` | TTS model identifier. Options include `"playai-tts"` (PlayAI Dialog, English), `"playai-tts-arabic"` (PlayAI Dialog, Arabic), `"canopylabs/orpheus-v1-english"` (Orpheus English with vocal direction support), and `"canopylabs/orpheus-arabic-saudi"` (Orpheus Arabic, Saudi dialect). |
| `voice` | `str` | `"Fritz-PlayAI"` | Voice identifier used for synthesis. For `"playai-tts"`, example voices include `"Fritz-PlayAI"`, `"Aaliyah-PlayAI"`, and `"Adelaide-PlayAI"`. For the Orpheus English model, available voices include `"troy"`, `"hannah"`, `"austin"`, `"diana"`, `"autumn"`, and `"daniel"`. |
| `speed` | `float` | `1.0` | Speaking speed multiplier. |
| `response_format` | `str` | `"wav"` | Audio container format for the returned audio. |
| `sample_rate` | `int` | `24000` | Output audio sample rate in Hz. |

Synthesized audio is streamed back to the caller after the
[LLM](/runtime-sdk/plugins/overview) produces a response.


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