Realtime API support is coming soon! Reach out to support@portkey.ai to be the first to know when LiveKit’s realtime model integration with the AI Gateway is available.

LiveKit is a powerful platform for building real-time voice and video applications. When combined with the AI Gateway, you get enterprise-grade features that make your LiveKit voice agents production-ready:

Unified AI Gateway - Single interface for 3,000+ LLMs with API key management
Centralized AI observability: Real-time usage tracking for 40+ key metrics and logs for every request
Governance - Real-time spend tracking, set budget limits and RBAC in your LiveKit agents
Security Guardrails - PII detection, content filtering, and compliance controls

This guide will walk you through integrating the AI Gateway with LiveKit’s STT-LLM-TTS pipeline to build enterprise-ready voice AI agents.

If you are an enterprise looking to deploy LiveKit agents in production, check out this section.

1. Setting up the AI Gateway

The AI Gateway lets you use 3,000+ LLMs with your LiveKit agents, with minimal configuration required. Let’s set up the core components in the AI Gateway that you’ll need for integration.

Connect your LLM`

To create a new integration:

Go to Integrations in Strata Cloud Manager
Click “Add Integration” and select OpenAI
Provision workspaces and budget/rate limits if required

When you create a new integration, the AI Gateway creates a unique provider slug for the integration that you can then use in your requests.

Create Default Config

Configs in the AI Gateway define how your requests are routed and can enable features like fallbacks, caching, and more.To create your config:

Go to Configs in Strata Cloud Manager

Create new config with:

{
    "provider":"@YOUR_PROVIDER_FROM_STEP1"
}

Save and note the Config ID for the next step

This basic config connects to your integration. You can add advanced features like caching, fallbacks, and guardrails later.

Configure AI Gateway API Key

Now create an AI Gateway API key and attach the config you created:

Go to API Keys in the AI Gateway
Create new API key
Select your config from Step 2
Generate and save your API key

Save your API key securely - you’ll need it for LiveKit integration.

2. Integrate the AI Gateway with LiveKit

Now that you have your AI Gateway components set up, let’s integrate them with LiveKit agents.

Installation

Install the required packages:

pip install \
  "livekit-agents[openai]~=1.0"

Configuration

llm=openai.LLM(model="gpt-4o", # your preferred model
               api_key="YOUR_PORTKEY_API_KEY", # you can also set OPENAI_API_KEY=<Your AI Gateway API key> in .env
               base_url="https://aigw.portkey.ai/v1", # the AI Gateway Base Url
               ),

Make sure your AI Gateway integration has sufficient budget and rate limits for your expected usage.

End-to-End Example using the AI Gateway and LiveKit

Build a simple voice assistant with Python in less than 10 minutes.

Setup

  pip install \
    "livekit-agents[deepgram,openai,cartesia,silero,turn-detector]~=1.0" \
    "livekit-plugins-noise-cancellation~=0.2" \
    "python-dotenv"

Add your .env file

DEEPGRAM_API_KEY=<Your Deepgram API Key>
OPENAI_API_KEY=<Your Gateway API Key>
CARTESIA_API_KEY=<Your Cartesia API Key>
LIVEKIT_API_KEY=<your API Key>
LIVEKIT_API_SECRET=<your API Secret>
LIVEKIT_URL=<your LiveKit server URL>

Full STT-to-TTS agent code

from dotenv import load_dotenv

from livekit import agents
from livekit.agents import AgentSession, Agent, RoomInputOptions
from livekit.plugins import (
    openai,
    cartesia,
    deepgram,
    noise_cancellation,
    silero,
)
from livekit.plugins.turn_detector.multilingual import MultilingualModel

load_dotenv()

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

async def entrypoint(ctx: agents.JobContext):
    session = AgentSession(
        stt=deepgram.STT(model="nova-3", language="multi"),
        llm=openai.LLM(model="gpt-4o",
                    api_key="YOUR_PORTKEY_API_KEY",
                    base_url="https://aigw.portkey.ai/v1",
                    ),
        tts=cartesia.TTS(),
        vad=silero.VAD.load(),
        turn_detection=MultilingualModel(),
    )

    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_input_options=RoomInputOptions(
            # LiveKit Cloud enhanced noise cancellation
            # - If self-hosting, omit this parameter
            # - For telephony applications, use `BVCTelephony` for best results
            noise_cancellation=noise_cancellation.BVC(),
        ),
    )

    await ctx.connect()

    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )

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

3. Set Up Enterprise Governance for Livekit

Why Enterprise Governance? If you are using Livekit inside your orgnaization, you need to consider several governance aspects:

Cost Management: Controlling and tracking AI spending across teams
Access Control: Managing which teams can use specific models
Usage Analytics: Understanding how AI is being used across the organisation
Security & Compliance: Maintaining enterprise security standards
Reliability: Ensuring consistent service across all users

The AI Gateway adds a comprehensive governance layer to address these enterprise needs. Let’s implement these controls step by step. Enterprise Implementation Guide

Step 1: Implement Budget Controls & Rate Limits

Integrations enable granular control over LLM access at the team/department level. This helps you:

Set up budget limits
Prevent unexpected usage spikes using Rate limits
Track departmental spending

Setting Up Department-Specific Controls:

Navigate to Integrations in Strata Cloud Manager and create a new Integration
Provision the integration to relevant workspaces with their own budgets

Step 2: Define Model Access Rules

As your AI usage scales, controlling which teams can access specific models becomes crucial. AI Gateway Configs provide this control layer with features like:

Access Control Features:

Model Restrictions: Limit access to specific models
Data Protection: Implement guardrails for sensitive data
Reliability Controls: Add fallbacks and retry logic

Example Configuration:

Here’s a basic configuration to route requests to OpenAI, specifically using GPT-4o:

{
  "override_params": { "model": "@openai-prod/gpt-4o" }
}

Create your config on the Configs page in Strata Cloud Manager. You’ll need the config ID for connecting to Livekit’s setup.

Configs can be updated anytime to adjust controls without affecting running applications.

Step 3: Implement Access Controls

Create User-specific API keys that automatically:

Track usage per user/team with the help of metadata
Apply appropriate configs to route requests
Collect relevant metadata to filter logs
Enforce access permissions

Create API keys through:

Example using Python SDK:For detailed key management instructions, see our API Keys documentation.

Step 4: Deploy & Monitor

After distributing API keys to your team members, your enterprise-ready Livekit setup is ready to go. Each team member can now use their designated API keys with appropriate access levels and budget controls. Apply your governance setup using the integration steps from earlier sections Monitor usage in Strata Cloud Manager:

Cost tracking by department
Model usage patterns
Request volumes
Error rates

Enterprise Features Now Available

Livekit now has:

Departmental budget controls
Model access governance
Usage tracking & attribution
Security guardrails
Reliability features

AI Gateway Features

Now that you have enterprise-grade Livekit setup, let’s explore the comprehensive features the AI Gateway provides to ensure secure, efficient, and cost-effective AI operations.

1. Comprehensive Metrics

Using the AI Gateway you can track 40+ key metrics including cost, token usage, response time, and performance across all your LLM providers in real time. You can also filter these metrics based on custom metadata that you can set in your configs. Learn more about metadata here.

2. Advanced Logs

The AI Gateway’s logging dashboard provides detailed logs for every request made to your LLMs. These logs include:

Complete request and response tracking
Metadata tags for filtering
Cost attribution and much more…

3. Unified Access to 3,000+ LLMs

You can easily switch between 3,000+ LLMs. Call various LLMs such as Anthropic, Gemini, Mistral, Azure OpenAI, Google Vertex AI, AWS Bedrock, and many more by simply changing the provider in your default config object.

4. Advanced Metadata Tracking

Using the AI Gateway, you can add custom metadata to your LLM requests for detailed tracking and analytics. Use metadata tags to filter logs, track usage, and attribute costs across departments and teams.

Custom Metata

5. Enterprise Access Management

Budget Controls

Set and manage spending limits across teams and departments. Control costs with granular budget limits and usage tracking.

Single Sign-On (SSO)

Enterprise-grade SSO integration with support for SAML 2.0, Okta, Azure AD, and custom providers for secure authentication.

Organisation Management

Hierarchical organisation structure with workspaces, teams, and role-based access control for enterprise-scale deployments.

Access Rules & Audit Logs

Comprehensive access control rules and detailed audit logging for security compliance and usage tracking.

6. Reliability Features

Fallbacks

Automatically switch to backup targets if the primary target fails.

Conditional Routing

Route requests to different targets based on specified conditions.

Load Balancing

Distribute requests across multiple targets based on defined weights.

Caching

Enable caching of responses to improve performance and reduce costs.

Smart Retries

Automatic retry handling with exponential backoff for failed requests

Budget Limits

Set and manage budget limits across teams and departments. Control costs with granular budget limits and usage tracking.

7. Advanced Guardrails

Protect your Project’s data and enhance reliability with real-time checks on LLM inputs and outputs. Leverage guardrails to:

Prevent sensitive data leaks
Enforce compliance with organisational policies
PII detection and masking
Content filtering
Custom security rules
Data compliance checks

Guardrails

Implement real-time protection for your LLM interactions with automatic detection and filtering of sensitive content, PII, and custom security rules. Enable comprehensive data protection while maintaining compliance with organisational policies.

FAQs

Can I use models other than OpenAI with LiveKit through the AI Gateway?

Yes! The AI Gateway supports 3,000+ LLMs. Simply integrate your preferred provider (Anthropic, Google, Cohere, etc.) and update your config accordingly. The LiveKit OpenAI client will work seamlessly with any provider through the AI Gateway.

How do I track costs for different voice agents?

Use metadata tags when creating AI Gateway headers to segment costs:

Add agent_type, department, or customer_id tags
View costs filtered by these tags in Strata Cloud Manager
Set up separate providers with budget limits for each use case

What happens if my primary LLM provider goes down?

Configure fallbacks in your AI Gateway config to automatically switch to backup providers. Your LiveKit agents will continue working without any code changes or downtime.

Can I implement custom business logic for my agents?

Yes! Use the AI Gateway’s hooks and guardrails to:

Filter sensitive information
Add custom headers or modify requests
Implement business-specific validation
Route requests based on custom logic

How do I migrate existing LiveKit agents to use the AI Gateway?

Migration is simple:

Create providers and configs in the AI Gateway
Update the OpenAI client initialization to use the AI Gateway’s base URL
Add AI Gateway headers with your API key and config
No other code changes needed!

Next Steps

Ready to build production voice AI?

For enterprise support and custom features for your LiveKit deployment, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action

​1. Setting up the AI Gateway

​2. Integrate the AI Gateway with LiveKit

​Installation

​Configuration

​End-to-End Example using the AI Gateway and LiveKit

​3. Set Up Enterprise Governance for Livekit

​Step 1: Implement Budget Controls & Rate Limits

​Setting Up Department-Specific Controls:

​Step 2: Define Model Access Rules

​Access Control Features:

​Example Configuration:

​Step 3: Implement Access Controls

​Step 4: Deploy & Monitor

​Enterprise Features Now Available

​AI Gateway Features

​1. Comprehensive Metrics

​2. Advanced Logs

​3. Unified Access to 3,000+ LLMs

​4. Advanced Metadata Tracking

Custom Metata

​5. Enterprise Access Management

Budget Controls

Single Sign-On (SSO)

Organisation Management

Access Rules & Audit Logs

​6. Reliability Features

Fallbacks

Conditional Routing

Load Balancing

Caching

Smart Retries

Budget Limits

​7. Advanced Guardrails

Guardrails

​FAQs

​Next Steps

1. Setting up the AI Gateway

2. Integrate the AI Gateway with LiveKit

Installation

Configuration

End-to-End Example using the AI Gateway and LiveKit

3. Set Up Enterprise Governance for Livekit

Step 1: Implement Budget Controls & Rate Limits

Setting Up Department-Specific Controls:

Step 2: Define Model Access Rules

Access Control Features:

Example Configuration:

Step 3: Implement Access Controls

Step 4: Deploy & Monitor

Enterprise Features Now Available

AI Gateway Features

1. Comprehensive Metrics

2. Advanced Logs

3. Unified Access to 3,000+ LLMs

4. Advanced Metadata Tracking

5. Enterprise Access Management

6. Reliability Features

7. Advanced Guardrails

FAQs

Next Steps