Session Management

The session management classes allow you to start and interact with agent sessions.

Session

The Session class is the primary way to start and interact with agent sessions.

from pipecatcloud.session import Session, SessionParams

session = Session(
    agent_name="my-agent",
    api_key="pk_...",
    params=SessionParams(use_daily=True)
)

Constructor Parameters

string

required

Name of the deployed agent to interact with.

string

required

Public API key for authentication.

SessionParams

Optional parameters to configure the session.

Methods

async

Starts a new session with the specified agent.ReturnsA dictionary containing session information. If use_daily is True, includes dailyRoom URL and dailyToken.RaisesAgentStartError: If the session fails to start due to missing API key, agent not found, agent not ready, or capacity limits.

SessionParams

The SessionParams class allows you to configure a session.

from pipecatcloud.session import SessionParams

params = SessionParams(
    data={"custom_field": "value"},
    use_daily=True,
    daily_room_properties={"enable_recording": "cloud"}
)

Parameters

Dict[str, Any]

default:"None"

Optional dictionary of data to pass to the agent. Must be JSON-serializable.

boolean

default:"False"

If True, creates a Daily WebRTC room for the session, enabling voice interaction.

Dict[str, Any]

default:"None"

Optional dictionary of properties to configure the Daily room. Only used when use_daily=True.See Daily API documentation for available properties.

Pipecat Server

Client SDKs

Pipecat Flows

Pipecat Cloud

CLI

Pipecat Context Hub

Session Management

Session

Constructor Parameters

Methods

SessionParams

Parameters

​Session

​Constructor Parameters

​Methods

​SessionParams

​Parameters

Session

Constructor Parameters

Methods

SessionParams

Parameters