Groq and LiveKit

Try out Groq Talk

See our voice assistant playground using Groq STT, LLM, and TTS

Groq ecosystem support

Groq provides fast AI inference in the cloud and on-prem AI compute centers. LiveKit Agents can integrate with the following Groq services:

• STT: Fast and cost-effective English or multilingual transcription based on whisper-large-v3.
• TTS: Fast English and Arabic text-to-speech based on playai-tts.
• LLM: Fast inference for open models like llama-3.1-8b-instant and more.

Getting started

Use the Voice AI quickstart to build a voice AI app with Groq. Select an STT-LLM-TTS pipeline model type and add the following components to build on Groq.

Install the Groq plugin:

pip install "livekit-agents[groq]~=1.0"

Add your Groq API key to your .env. file:

GROQ_API_KEY=<Your Groq API Key>

Use Groq components to initialize your AgentSession:

from livekit.plugins import groq

# ...

# in your entrypoint function
session = AgentSession(
    stt=groq.STT(
        model="whisper-large-v3-turbo",
        language="en",
    ),
    llm=groq.LLM(
        model="llama3-8b-8192"
    ),
    tts=groq.TTS(
      model="playai-tts",
      voice="Arista-PlayAI",
    ),
    # ... vad, turn_detection, etc.
)

LiveKit Agents overview

LiveKit Agents is an open source framework for building realtime AI apps in Python and Node.js. It supports complex voice AI workflows with multiple agents and discrete processing steps, and includes built-in load balancing.

LiveKit provides SIP support for telephony integration and full-featured frontend SDKs in multiple languages. It uses WebRTC transport for end-user devices, enabling high-quality, low-latency realtime experiences. To learn more, see LiveKit Agents.

Groq plugin documentation

The following links provide more information on each available Groq component in LiveKit Agents.