@fishaudio/agent-client

Framework-agnostic JavaScript/TypeScript SDK for embedding Fish Audio voice agents into any website or web app: realtime voice over WebRTC, live transcripts, text input, and client tools — behind one small, event-driven API.

Using React? @fishaudio/agent-react wraps this SDK in hooks and components.

Installation

npm install @fishaudio/agent-client

Quickstart

import { AgentSession } from "@fishaudio/agent-client";

// Session token from your backend — or { agentId } for a public agent.
const sessionToken = await fetch("/api/voice-session", { method: "POST" }).then((r) => r.json());

const session = await AgentSession.start({
  sessionToken,
  callbacks: {
    onModeChange: (mode) => setOrbState(mode), // "listening" | "thinking" | "speaking"
    onMessage: ({ role, text }) => renderChatBubble(role, text),
    onDisconnect: ({ reason }) => showCallEnded(reason),
  },
});

// Later:
session.sendUserMessage("Can you summarize that?");
await session.end();

Starting a session requests microphone access; call start() from a user gesture (button click) for the best permission and autoplay behavior.

Documentation

• Quickstart — first call, with or without a backend.
• Authentication — server-created session tokens vs. public agents.
• Sessions — start() options, the session API, lifecycle and reconnection.
• Events — event reference and live transcripts.
• Client tools — let the agent call functions in the browser.
• Customization — per-session overrides and dynamic variables.
• Errors — FishAgentError codes.