Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/DecartAI/sdk/llms.txt

Use this file to discover all available pages before exploring further.

This example demonstrates how to build a secure real-time video transformation application using Next.js. It uses the App Router with client tokens to keep your API key secure on the server.

​
What You’ll Build

A Next.js application that:
  • Issues short-lived client tokens from a server API route
  • Uses client tokens in the browser to connect to Decart’s real-time API
  • Captures and transforms webcam video in real-time
  • Never exposes your API key to the client

​
Prerequisites

  • Node.js 18 or higher
  • A Decart API key
  • A webcam for testing

​
Setup

1

Clone and navigate to the example

git clone https://github.com/decartai/sdk
cd sdk/examples/nextjs-realtime
2

Configure your API key

Create a .env.local file and add your API key:
DECART_API_KEY=your-api-key-here
Use .env.local in Next.js to ensure environment variables are not exposed to the client.
3

Install dependencies

From the repository root:
pnpm install
pnpm build
4

Start the development server

cd examples/nextjs-realtime
pnpm dev
Open http://localhost:3000 in your browser.

​
Architecture

Browser → /api/realtime-token → Server (creates token) → Decart API
        ← Client Token ←
        → Realtime Connection (using client token) → Decart API
The client token is short-lived and scoped to real-time API access only, keeping your main API key secure.

​
Server: Token Generation API Route

The /api/realtime-token/route.ts endpoint creates client tokens: 
import { createDecartClient } from "@decartai/sdk";
import { NextResponse } from "next/server";

const DECART_API_KEY = process.env.DECART_API_KEY;

export async function POST() {
  try {
    if (!DECART_API_KEY) {
      return NextResponse.json(
        { error: "DECART_API_KEY is not set" },
        { status: 500 }
      );
    }

    const client = createDecartClient({
      apiKey: DECART_API_KEY,
    });
    const token = await client.tokens.create();

    return NextResponse.json(token);
  } catch (error) {
    console.error("Failed to create client token:", error);
    return NextResponse.json(
      { error: "Failed to create client token" },
      { status: 500 }
    );
  }
}

​
Client: Main Page Component

The app/page.tsx component manages the prompt state: 
"use client";

import { useState } from "react";
import { VideoStream } from "../components/video-stream";

export default function Home() {
  const [prompt, setPrompt] = useState("anime style, vibrant colors");

  return (
    <main style={{ padding: "2rem", fontFamily: "system-ui" }}>
      <h1>Decart Realtime Demo</h1>

      <div style={{ marginBottom: "1rem" }}>
        <label>
          Style prompt:
          <input
            type="text"
            value={prompt}
            onChange={(e) => setPrompt(e.target.value)}
            style={{ marginLeft: "0.5rem", width: "300px", padding: "0.5rem" }}
          />
        </label>
      </div>

      <VideoStream prompt={prompt} />
    </main>
  );
}

​
Client: VideoStream Component

The components/video-stream.tsx component fetches a token and connects: 
"use client";

import {
  createDecartClient,
  type DecartSDKError,
  models,
  type RealTimeClient,
} from "@decartai/sdk";
import { useEffect, useRef, useState } from "react";

interface VideoStreamProps {
  prompt: string;
}

export function VideoStream({ prompt }: VideoStreamProps) {
  const inputRef = useRef<HTMLVideoElement>(null);
  const outputRef = useRef<HTMLVideoElement>(null);
  const realtimeClientRef = useRef<RealTimeClient | null>(null);
  const [status, setStatus] = useState<string>("idle");

  useEffect(() => {
    let mounted = true;

    async function start() {
      try {
        const model = models.realtime("mirage_v2");

        setStatus("requesting camera...");
        const stream = await navigator.mediaDevices.getUserMedia({
          video: {
            frameRate: model.fps,
            width: model.width,
            height: model.height,
          },
        });

        if (!mounted) return;

        if (inputRef.current) {
          inputRef.current.srcObject = stream;
        }

        // Fetch client token from our backend API
        const tokenResponse = await fetch("/api/realtime-token", {
          method: "POST",
        });
        if (!tokenResponse.ok) {
          throw new Error("Failed to get client token");
        }
        const { apiKey } = await tokenResponse.json();

        if (!mounted) return;

        setStatus("connecting...");

        const client = createDecartClient({ apiKey });

        const realtimeClient = await client.realtime.connect(stream, {
          model,
          onRemoteStream: (transformedStream: MediaStream) => {
            if (outputRef.current) {
              outputRef.current.srcObject = transformedStream;
            }
          },
          initialState: {
            prompt: { text: prompt, enhance: true },
          },
        });

        realtimeClientRef.current = realtimeClient;

        // Subscribe to events
        realtimeClient.on("connectionChange", (state) => {
          setStatus(state);
        });

        realtimeClient.on("error", (error: DecartSDKError) => {
          setStatus(`error: ${error.message}`);
        });
      } catch (error) {
        setStatus(`error: ${error}`);
      }
    }

    start();

    return () => {
      mounted = false;
      realtimeClientRef.current?.disconnect();
    };
  }, []);

  // Update prompt when it changes
  useEffect(() => {
    if (realtimeClientRef.current?.isConnected()) {
      realtimeClientRef.current.setPrompt(prompt, { enhance: true });
    }
  }, [prompt]);

  return (
    <div>
      <p>Status: {status}</p>
      <div style={{ display: "flex", gap: "1rem" }}>
        <div>
          <h3>Input</h3>
          <video ref={inputRef} autoPlay muted playsInline width={400} />
        </div>
        <div>
          <h3>Styled Output</h3>
          <video ref={outputRef} autoPlay playsInline width={400} />
        </div>
      </div>
    </div>
  );
}

​
Key Concepts

​
Client Tokens

Client tokens provide secure, temporary access to the real-time API: 
// Server-side: Create token
const token = await client.tokens.create();

// Client-side: Fetch token
const response = await fetch("/api/realtime-token", { method: "POST" });
const { apiKey } = await response.json();

// Use token to create client
const client = createDecartClient({ apiKey });

​
Benefits of Client Tokens

  1. Security: Your main API key never leaves the server
  2. Scoped Access: Tokens only work with the real-time API
  3. Time-Limited: Tokens expire automatically
  4. Simple: Drop-in replacement for API keys in client code

​
Next.js App Router

This example uses Next.js App Router features:
  • Server Actions: API routes in app/api/ directory
  • Client Components: Interactive UI with "use client" directive
  • Environment Variables: .env.local for server-side secrets

​
Error Handling

Handle token fetch and connection errors: 
const tokenResponse = await fetch("/api/realtime-token", {
  method: "POST",
});

if (!tokenResponse.ok) {
  throw new Error("Failed to get client token");
}

​
Available Models

You can use different real-time models:
  • mirage_v2 - MirageLSD video restyling (recommended)
  • mirage - Original MirageLSD model
  • lucy_v2v_720p_rt - Lucy for video editing (add/change objects)
  • lucy_2_rt - Lucy 2 with reference image support

Build docs developers (and LLMs) love

Get started for freeTalk to us