Simulate your voice agent making a call to a user.
How it works
- Set the
agent_url for your websocket endpoint in your config.
- Calibrate opens a WebSocket to your agent and connects as a client.
- The simulated user (persona + scenario) speaks audio streams to your agent.
- Your agent’s audio streams back and Calibrate transcribes it.
- The conversation is appended and new simulated user audio is sent to your agent.
- Once the call is complete, metrics are computed over the resulting transcript.
Configuration
Your agent must speak Pipecat’s WebSocket frame protocol with the same
serializer (protobuf). A non-pipecat socket won’t work.
Example