Get Started

Once you've built your Omniagent, you can deploy it to any channel — or all of them at the same time. Because the agent is a single, persistent resource, the same voice, personality, knowledge, and memory are available on every surface. A user can start a conversation on the web and continue it over the phone — it's the same agent.

Pick one channel to start, or deploy to several at once. Each channel guide walks you through the full setup.

Channels

WebRTC

Browser-based experience with audio and video via the Web SDK

WebSockets

Audio-only connection for custom integrations

VoIP

Answer phone calls via Twilio

SIP

Bring your own SIP trunk

Kiosk

In-person, walk-up conversations on a Napster Station

Session configuration

Configure per-session settings like memory, user context, and tags.

Configure a Session

Memory, user identity, tags, and other session-level settings

Messaging

Once connected, your client communicates with the agent through events and commands. The server pushes events as the conversation progresses, and your client can send text messages and update session settings in real time.

Server Events

Server-to-client events published during a session

Client Commands

Send commands and update session settings from your client