Using SIP participant attributes

You can use SIP participant attributes to create different workflows based on the caller. For example, look up customer information in a database to identify the caller.

Examples

The following examples use template apps as a starting point. If you completed the Accepting incoming calls quickstart, you can use the agent you created in Step 2: Creating an AI voice agent.

Otherwise, to create a template app, run the following LiveKit CLI command. For example, to create a voice-pipeline-agent-python template app:

lk app create --template voice-pipeline-agent-python

You can find a full list of Public template apps in the LiveKit examples repo.

The following example is based off the voice-pipeline-agent-python example app. The entrypoint function is modified to identify SIP participants.

Add the following line near the top of your agent.py file to import the rtc module:
```
from livekit import rtc
```

Replace the entrypoint function with the following code:

async def entrypoint(ctx: JobContext):
    initial_ctx = llm.ChatContext().append(
        role="system",
        text=(
            "You are a voice assistant created by LiveKit. Your interface with users will be voice. "
            "You should use short and concise responses, and avoiding usage of unpronouncable punctuation. "
            "You were created as a demo to showcase the capabilities of LiveKit's agents framework."
        ),
    )

    logger.info(f"connecting to room {ctx.room.name}")
    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)

    # Wait for the first participant to connect
    participant = await ctx.wait_for_participant()
    logger.info(f"starting voice assistant for participant {participant.identity}")

    # Default Deepgram model
    dg_model = "nova-2-general"

    # Check if the participant is a SIP participant
    if participant.kind == rtc.ParticipantKind.PARTICIPANT_KIND_SIP:
        # Use a Deepgram model better suited for phone calls
        db_model = "nova-2-phonecall"

        # Do something here based on SIP participant attributes
        # For example, look up customer information using their phone number

        # If this caller is calling from a specific phone number, do something
        if participant.attributes['sip.phoneNumber'] == '+15105550100':
            logger.info("Caller phone number is +1-510-555-0100")

    # This project is configured to use Deepgram STT, OpenAI LLM and TTS plugins
    # Other great providers exist like Cartesia and ElevenLabs
    # Learn more and pick the best one for your app:
    # https://docs.livekit.io/agents/plugins
    assistant = VoicePipelineAgent(
        vad=ctx.proc.userdata["vad"],
        stt=deepgram.STT(model=dg_model),
        llm=openai.LLM(model="gpt-4o-mini"),
        tts=openai.TTS(),
        chat_ctx=initial_ctx,
    )

    assistant.start(ctx.room, participant)

    # The agent should be polite and greet the user when it joins :)
    await assistant.say("Hey, how can I help you today?", allow_interruptions=True)