Groq

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:

export GROQ_API_KEY=<key>

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

from zrt.plugins import GroqTTS

tts = GroqTTS()

# Pipeline(tts=tts, ...)

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 produces a response.