Skip to main content
Use Emby’s OpenAI-compatible API in your Next.js application for AI-powered features.

​
Prerequisites

  • Node.js 18+ installed
  • An Emby account with an API key
  • A Next.js project (or create one)

​
Installation

npm install openai

​
Configuration

1

​
Set Environment Variables

Create or update your .env.local file:
EMBY_API_KEY=your-api-key-here
EMBY_BASE_URL=https://dev.emby.ai/v1
Never commit your API key to version control. Add .env.local to your .gitignore file.
2

​
Create the API Client

Create a utility file to initialize the OpenAI client with Emby’s endpoint:
// lib/emby.ts
import OpenAI from 'openai';

export const emby = new OpenAI({
  apiKey: process.env.EMBY_API_KEY,
  baseURL: process.env.EMBY_BASE_URL,
});
3

​
Create an API Route

Create a Next.js API route to handle AI requests:
// app/api/chat/route.ts
import { emby } from '@/lib/emby';
import { NextRequest, NextResponse } from 'next/server';

export async function POST(request: NextRequest) {
  const { messages } = await request.json();

  const completion = await emby.chat.completions.create({
    model: 'gpt-4o',
    messages,
  });

  return NextResponse.json(completion.choices[0].message);
}
4
For a better user experience, use streaming responses:
// app/api/chat/route.ts
import { emby } from '@/lib/emby';
import { NextRequest } from 'next/server';

export async function POST(request: NextRequest) {
  const { messages } = await request.json();

  const stream = await emby.chat.completions.create({
    model: 'gpt-4o',
    messages,
    stream: true,
  });

  const encoder = new TextEncoder();
  const readable = new ReadableStream({
    async start(controller) {
      for await (const chunk of stream) {
        const text = chunk.choices[0]?.delta?.content || '';
        controller.enqueue(encoder.encode(text));
      }
      controller.close();
    },
  });

  return new Response(readable, {
    headers: { 'Content-Type': 'text/plain; charset=utf-8' },
  });
}

​
Example Usage

​
Client Component

// components/Chat.tsx
'use client';

import { useState } from 'react';

export function Chat() {
  const [input, setInput] = useState('');
  const [response, setResponse] = useState('');
  const [loading, setLoading] = useState(false);

  const handleSubmit = async (e: React.FormEvent) => {
    e.preventDefault();
    setLoading(true);
    setResponse('');

    const res = await fetch('/api/chat', {
      method: 'POST',
      headers: { 'Content-Type': 'application/json' },
      body: JSON.stringify({
        messages: [{ role: 'user', content: input }],
      }),
    });

    const reader = res.body?.getReader();
    const decoder = new TextDecoder();

    while (reader) {
      const { done, value } = await reader.read();
      if (done) break;
      setResponse((prev) => prev + decoder.decode(value));
    }

    setLoading(false);
  };

  return (
    <form onSubmit={handleSubmit}>
      <input
        value={input}
        onChange={(e) => setInput(e.target.value)}
        placeholder="Ask something..."
      />
      <button type="submit" disabled={loading}>
        {loading ? 'Thinking...' : 'Send'}
      </button>
      {response && <p>{response}</p>}
    </form>
  );
}

​
Available Models

Use any Emby supported model: 
// Popular choices
const model = 'gpt-4o';           // Fast and capable
const model = 'gpt-5';            // Most powerful
const model = 'claude-sonnet-4-5'; // Anthropic's latest

​
Need Help?

WhatsApp Support

Chat with us instantly

Book a Call

For enterprise support