Groq STT integration guide

Available in

Python

Node.js

Experience Groq's fast STT in a LiveKit-powered playground

Overview

Groq provides fast STT using fine-tuned and distilled models based on Whisper V3 Large. With LiveKit's Groq integration and the Agents framework, you can build AI voice applications with fluent and conversational voices.

Quick reference

This section includes a basic usage example and some reference material. For links to more detailed documentation, see Additional resources.

Installation

Install the plugin from PyPI:

pip install "livekit-agents[groq]~=1.2"

For Node.js, support for Groq STT is available using the OpenAI plugin.

pnpm add @livekit/agents-plugin-openai@1.x

Authentication

The Groq plugin requires a Groq API key.

Set GROQ_API_KEY in your .env file.

Usage

Use Groq STT in your AgentSession or as a standalone transcription service. For example, you can use this STT in the Voice AI quickstart.

from livekit.plugins import groq
   
session = AgentSession(
   stt=groq.STT(
      model="whisper-large-v3-turbo",
      language="en",
   ),
   # ... tts, llm, vad, turn_detection, etc.
)

import * as openai from '@livekit/agents-plugin-openai';

const session = new voice.AgentSession({
    stt: new openai.STT.withGroq(
        model: "whisper-large-v3-turbo"
    ),
    // ... tts, llm, vad, turn_detection, etc.
});

Parameters

This section describes some of the available parameters. See the plugin reference links in the Additional resources section for a complete list of all available parameters.

modelstringOptionalDefault: whisper-large-v3-turbo

Name of the STT model to use. For help with model selection, see the Groq STT documentation.

languagestringOptionalDefault: en

Language of the input audio in ISO-639-1 format.

promptstringOptional

Prompt to guide the model's style or specify how to spell unfamiliar words. 224 tokens max.