Build with LiveKit - SambaNova Integration Guide

LiveKit is an open-source project that enables scalable, multi-user conferencing with WebRTC. It provides the tools you need to add real-time video, audio, and data capabilities to your applications.

Prerequisites

A SambaCloud account
A SambaNova API key
A LiveKit Cloud account or self-hosted LiveKit server, with LIVEKIT_URL, LIVEKIT_API_KEY, and LIVEKIT_API_SECRET
Python 3.11.5 or later

Installation and setup

Create and activate a virtual environment

macOS/Linux:

python -m venv .venv
source .venv/bin/activate

Windows:

python -m venv .venv
.venv\Scripts\activate

Install LiveKit agents

pip install "livekit-agents[openai,silero,deepgram,cartesia,turn-detector]~=1.0"

Set environment variables

export SAMBANOVA_API_KEY="your-sambanova-api-key"
export SAMBANOVA_URL="https://api.sambanova.ai/v1"

Example use cases

You can combine LiveKit with SambaCloud models to create powerful, real-time AI agents. Some common applications include:

Multimodal assistants – Support text, voice, and screen sharing with an AI assistant.
Telehealth – Enable real-time AI support during virtual medical consultations.
Call centers – Automate inbound and outbound customer support with AI voice agents.
Real-time translation – Translate conversations instantly across languages.

Example - voice agent with SambaCloud

The following example shows how to build a voice AI agent using LiveKit with SambaCloud LLM models:

from livekit import agents
from livekit.agents import AgentSession, Agent, RoomInputOptions
from livekit.plugins import openai, cartesia, noise_cancellation, silero
import os

SAMBANOVA_URL = os.getenv("SAMBANOVA_URL")
SAMBANOVA_API_KEY = os.getenv("SAMBANOVA_API_KEY")

class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(instructions="You are a helpful voice AI assistant.")

llm = openai.LLM(
    model="Llama-4-Maverick-17B-128E-Instruct",
    api_key=SAMBANOVA_API_KEY,
    base_url=SAMBANOVA_URL,
)

async def entrypoint(ctx: agents.JobContext):
    session = AgentSession(
        stt=cartesia.STT(
           model="ink-whisper"
        ),
        llm=llm,
        tts=cartesia.TTS(),
        vad=silero.VAD.load(),
    )
    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_input_options=RoomInputOptions(
            noise_cancellation=noise_cancellation.BVC(),
        ),
    )
    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )

if __name__ == "__main__":
    agents.cli.run_app(agents.WorkerOptions(entrypoint_fnc=entrypoint))

LiveKit documentation

See LiveKit documentation for more details.

Troubleshooting

Agent fails or returns None for base URL

Ensure SAMBANOVA_URL is exported: export SAMBANOVA_URL=https://api.sambanova.ai/v1.

Authentication error or 401 Unauthorized

Verify SAMBANOVA_API_KEY is set. Get a new key from the SambaNova API dashboard.

ModuleNotFoundError: No module named 'livekit'

Run pip install "livekit-agents[openai,silero,deepgram,cartesia,turn-detector]~=1.0" with the virtual environment active.

Overview

Developer tools

Frameworks

Interfaces and low-code

Data and infrastructure

Multimodal

Evaluation and monitoring

LiveKit integration guide

Prerequisites

Installation and setup

Example use cases

Example - voice agent with SambaCloud

LiveKit documentation

Troubleshooting

​Prerequisites

​Installation and setup

​Example use cases

​Example - voice agent with SambaCloud

​LiveKit documentation

​Troubleshooting

Prerequisites

Installation and setup

Example use cases

Example - voice agent with SambaCloud

LiveKit documentation

Troubleshooting