LiveKit STS Integration

Prerequisite

If you haven't set up a voice agent in the Paygent dashboard yet, please follow our setup guide first. You'll need an Agent ID to start tracking.

Automatically track unified Speech-to-Speech (STS) usage for LiveKit Agents using the LiveKitPaygentHook. This is the recommended way to track multimodal sessions.

Simplified Workflow

The LiveKit hook handles the entire session lifecycle, from initializing the voice session to tracking multimodal usage and setting the final indicator.

Implementation Steps

Initialize Client

Initialize the Paygent Client at the global level.

Attach Hook

The hook automatically calls initialize_voice_session when the room is joined.

livekit_sts_agent.py

1from paygent_sdk import Client
2from paygent_sdk.wrappers import LiveKitPaygentHook
3from paygent_sdk.models import STSConfig
4
5# 1. Initialize Paygent
6paygent = Client("your-paygent-api-key")
7
8@server.rtc_session()
9async def sts_agent(ctx: JobContext):
10    # LiveKit Realtime Model setup
11    model = openai.realtime.RealtimeModel()
12    
13    # ... setup agent and session ...
14
15    # 2. Attach Paygent Hook with STSConfig
16    # This automatically handles initialize_voice_session, tracking, and set_voice_indicator
17    hook = LiveKitPaygentHook(
18        paygent_client=paygent,
19        agent_id="your-external-agent-id",
20        customer_name="your-customer-name",
21        customer_id="your-customer-id",
22        session_id=ctx.job.id,
23        indicator_name="sts-call-completed",
24        sts_config=STSConfig(
25            model="gpt-realtime-2025-08-28",
26            provider="openai"
27        )
28    )
29    hook.attach(session)
30
31    await session.start(agent, room=ctx.room)

Voice Tracking

OpenAI Realtime

Was this page helpful?

Need help? Contact us at support@withpaygent.com