Python Outbound Call Agent

LiveKit Agents Docs • LiveKit Cloud • Blog

This example demonstrates an full workflow of an AI agent that makes outbound calls. It uses LiveKit SIP and Python Agents Framework.

It has two modes:

• VoicePipelineAgent: uses a voice pipeline of STT, LLM, and TTS for the call.
• MultimodalAgent: uses OpenAI's realtime speech to speech model.

The guide for this example is available at https://docs.livekit.io/agents/quickstarts/outbound-calls/. Make sure a SIP outbound trunk is configured before trying this example.

Features

This example demonstrates the following features:

• Making outbound calls
• Detecting voicemail
• Looking up availability via function calling
• Detecting intent to end the call

Dev Setup

Clone the repository and install dependencies to a virtual environment:

cd outbound-caller-python
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python agent.py download-files

Set up the environment by copying .env.example to .env.local and filling in the required values:

• LIVEKIT_URL
• LIVEKIT_API_KEY
• LIVEKIT_API_SECRET
• OPENAI_API_KEY
• SIP_OUTBOUND_TRUNK_ID
• DEEPGRAM_API_KEY - optional, only needed for VoicePipelineAgent

Run the agent:

python3 agent.py dev

Now, your worker is running, and waiting for dispatches in order to make outbound calls.

Making a call

You can dispatch an agent to make a call by using the lk CLI:

lk dispatch create \
  --new-room \
  --agent-name outbound-caller \
  --metadata '+1234567890'