WebRTC (browser)

Use WebRTCSession in the browser for WebRTC voice. Mint the credential on the server with Client.generateSessionToken and TRANSPORT_WEBRTC, then pass webrtc_token (LiveKit media-room JWT), url, room, and identity to the client. The response also includes a platform token (session JWT) for other APIs; use webrtc_token for WebRTCSession.connect.

Session token

API reference for the session-token request and response fields.

JavaScript SDK

Package install and SDK entry points.

Connection (message types)

WebSocket Session message catalog. WebRTCSession uses the same event names for signaling except it does not emit response_audio (agent speech is only on the WebRTC audio path into remoteAudioContainer).

Prerequisites

@vatel/sdk
Organization API key on the server only, agent UUID, WebRTC enabled on your stack

generateSessionToken (WebRTC)

import { Client, TRANSPORT_WEBRTC } from "@vatel/sdk";

const client = new Client({
  baseUrl: process.env.VATEL_BASE_URL ?? "https://api.vatel.ai",
  getToken: () => process.env.VATEL_API_KEY,
});

const { data, status } = await client.generateSessionToken(agentId, {
  transport: TRANSPORT_WEBRTC,
});

On the client, call WebRTCSession.connect with data.webrtc_token as token (the LiveKit media-room JWT), plus data.url and data.room - not data.token (the platform session JWT for WebSocket and other APIs). data.identity is part of the WebRTC payload. Check status and data for failures like any other SDK call.

Connect WebRTCSession (client)

import { WebRTCSession } from "@vatel/sdk";

const session = new WebRTCSession({
  remoteAudioContainer: document.getElementById("remote-audio"),
});

await session.connect({
  token: credential.webrtc_token,
  url: credential.url,
  room: credential.room,
});

await session.start();
await session.setMicrophoneEnabled(true);

credential is the response from the generateSessionToken result.

Session events

WebRTCSession uses the same signaling-style events as a WebSocket Session, except response_audio is not fired - agent audio is delivered only as a remote media stream (attach with remoteAudioContainer or your own playback). Subscribe with session.on(eventName, (msg) => { ... }). Each msg has type, timestamp, and data (fields depend on type).

Event	Purpose	Typical `msg.data`
`session_started`	Session is live	`id` - session identifier
`session_ended`	Session closed	May be an empty object; treat as end-of-call
`response_text`	Agent text for the current turn	`text`, `turn_id`
`input_audio_transcript`	STT of user speech	`transcript`
`speech_started`	User speech detected (VAD)	`emulated` - if `true`, VAD did not fire but a transcript arrived, so start-of-speech is synthetic
`speech_stopped`	User speech segment ended (VAD)	Usually empty
`interruption`	User cut off the agent while it was speaking	Usually empty
`tool_call`	Agent invoked a client tool	`toolCallId`, `toolName`, `arguments` (array of parameter descriptors with optional `value`)

For base64 response_audio chunks, use a WebSocket Session instead of WebRTCSession. Reply to tools with session.sendToolCallOutput(toolCallId, outputString) (async in some builds; use .catch(...) if needed).

session.on("session_started", (msg) => {
  console.log("session", msg.data?.id);
});
session.on("session_ended", () => console.log("ended"));
session.on("response_text", (msg) => console.log("agent:", msg.data?.text));
session.on("input_audio_transcript", (msg) => console.log("you:", msg.data?.transcript));
session.on("speech_started", (msg) => console.log("speech", msg.data?.emulated ? "emulated" : "vad"));
session.on("speech_stopped", () => console.log("speech stopped"));
session.on("interruption", () => console.log("interruption"));
session.on("tool_call", async (msg) => {
  const id = msg.data?.toolCallId;
  if (id) await session.sendToolCallOutput(id, "ok").catch(() => {});
});

Topic	Link
Browser voice demo (Next.js)	Next.js
SDK overview	JavaScript SDK

Overview

Configure

Deploy

Monitor

Integrations

Session token

JavaScript SDK

Connection (message types)

Prerequisites

generateSessionToken (WebRTC)

Connect WebRTCSession (client)

Session events

See also

Session token

JavaScript SDK

Connection (message types)

​Prerequisites

​generateSessionToken (WebRTC)

​Connect WebRTCSession (client)

​Session events

​See also

Prerequisites

generateSessionToken (WebRTC)

Connect WebRTCSession (client)

Session events

See also