The Napster Omniagent API supports six channels. Each channel is a different transport — how you connect. You can deploy the same agent to multiple channels simultaneously.
Available channels
| Channel | Description | Modality |
|---|---|---|
| WebRTC | Browser-based audio and video via the Web SDK. Embeds directly into any web page. | Audio + Video |
| WebSocket | Persistent connection for custom integrations. Supports audio or text-only. | Audio or Text |
| VoIP | Answer phone calls via Twilio, Telnyx, Vonage, or any VoIP provider. No SIP trunk required — just a webhook URL. | Voice |
| SIP (inbound) | Receive calls via your own SIP trunk for enterprise telephony integration. | Voice |
| SIP (outbound) | Agent proactively dials a phone number and initiates the conversation. See below. | Voice |
| Kiosk | In-person, walk-up conversations on a Napster Station device. | Audio + Video |
Outbound SIP calls
Napster agents can now initiate outbound SIP calls — the agent proactively dials a phone number and starts the conversation. This enables use cases such as:
- Proactive outreach — agent calls a customer to follow up, confirm an appointment, or deliver information
- Agent-led sales or support initiation
- Scheduled callback workflows
To trigger an outbound SIP call, configure your SIP channel on the agent and call the outbound call endpoint with the target phone number. The agent will dial out and begin the conversation when the call is answered. Full reference: developers.napster.com/docs/deploying-your-omniagent/phone
Text-only sessions
WebSocket sessions support a text modality — a typed chat with no voice and no avatar. Set modality: "text" when creating a WebSocket connection. See Text-Only WebSocket Sessions for details.
Session start performance
Session startup for the WebRTC channel has been improved, making agents feel more responsive when a user first interacts with them. Developers can also optionally enable audio-first startup — the agent's audio initialises before video is fully ready, giving an even faster-feeling experience for users. See the Web SDK docs for how to enable audio-first startup.
Typical latency
~300ms response latency across all channels. The platform supports approximately 30 languages across all channels.
For channel-specific setup guides, see the Deploying your Omniagent section of the developer docs.