Fix Realtime API: correct model name, remove beta header, fix session flow

[Copilot]

Previous implementation used a non-existent model (gpt-realtime-1.5) and included the beta-only OpenAI-Beta: realtime=v1 header, causing OpenAI to accept the WebSocket upgrade then immediately close with code 1000.

Server (server/index.ts)

• Default model: gpt-realtime-1.5 → gpt-4o-realtime-preview
• Removed OpenAI-Beta: realtime=v1 header (GA API rejects it)
• Abnormal close codes (≠ 1000/1001) now logged as errors and forwarded to the client as an error event before closing

Client (src/services/providers/openai.ts)

• Session flow fixed: configureSession() now fires on session.created (not ws.onopen), which is the correct Realtime API handshake sequence. This also eliminates the double onConnected() call that occurred when both session.created and session.updated resolved the same handler.
• ws.onclose during connecting state now rejects the promise and surfaces an error to the UI instead of silently transitioning to idle
• sendImage: image field renamed to image_url — correct field name for input_image content in the GA API
• Error events log the full event object for easier debugging

// Before: sent config on socket open, before session existed
this.ws.onopen = () => { this.configureSession(); };

// After: wait for session.created, then configure
case 'session.created':
  this.configureSession(); // sends session.update
  break;
case 'session.updated':
  this.sessionConfigured = true;
  this.events?.onConnected();
  resolveConnect?.();
  break;

Config

• .env.example updated to reflect gpt-4o-realtime-preview

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Redo: #3</issue_title>
<issue_description>#3

That was a bad PR. The client disconnects immediately. Did you follow the docs I shared with you? Ensure that you are using realtime-1.5 and that you use the correct syntax.

Make sure you surface or log any OpenAI errors. Understand that although this is optimized for speech-to-speech we are more interested in its high speed and updates and will mostly use it as image-totext (we show it screenshots and it produces notes).

Realtime API

Build low-latency, multimodal LLM applications with the Realtime API.

The OpenAI Realtime API enables low-latency communication with models that natively support speech-to-speech interactions as well as multimodal inputs (audio, images, and text) and outputs (audio and text). These APIs can also be used for realtime audio transcription.
Voice agents

One of the most common use cases for the Realtime API is building voice agents for speech-to-speech model interactions in the browser. Our recommended starting point for these types of applications is the Agents SDK for TypeScript, which uses a WebRTC connection to the Realtime model in the browser, and WebSocket when used on the server.

import { RealtimeAgent, RealtimeSession } from "@openai/agents/realtime";

const agent = new RealtimeAgent({
name: "Assistant",
instructions: "You are a helpful assistant.",
});

const session = new RealtimeSession(agent);

// Automatically connects your microphone and audio output
await session.connect({
apiKey: "",
});

Voice Agent Quickstart

Follow the voice agent quickstart to build Realtime agents in the browser.

To use the Realtime API directly outside the context of voice agents, check out the other connection options below.
Connection methods

While building voice agents with the Agents SDK is the fastest path to one specific type of application, the Realtime API provides an entire suite of flexible tools for a variety of use cases.

There are three primary supported interfaces for the Realtime API:
WebRTC connection

Ideal for browser and client-side interactions with a Realtime model.
WebSocket connection

Ideal for middle tier server-side applications with consistent low-latency network connections.
SIP connection

Ideal for VoIP telephony connections.

Depending on how you’d like to connect to a Realtime model, check out one of the connection guides above to get started. You’ll learn how to initialize a Realtime session, and how to interact with a Realtime model using client and server events.
API Usage

Once connected to a realtime model using one of the methods above, learn how to interact with the model in these usage guides.

[Prompting guide](https://developers.openai.com/api/docs/guides/realtime-models-prompting): learn tips and best practices for prompting and steering Realtime models.
[Managing conversations](https://developers.openai.com/api/docs/guides/realtime-conversations): Learn about the Realtime session lifecycle and the key events that happen during a conversation.
[Webhooks and server-side controls](https://developers.openai.com/api/docs/guides/realtime-server-controls): Learn how you can control a Realtime session on the server to call tools and implement guardrails.
[Managing costs](https://developers.openai.com/api/docs/guides/realtime-costs): Learn how to monitor and optimize your usage of the Realtime API.
[Realtime audio transcription](https://developers.openai.com/api/docs/guides/realtime-transcription): Transcribe audio streams in real time over a WebSocket connection.

Beta to GA migration

There are a few key differences between the interfaces in the Realtime beta API and the recently released GA API. Expand the topics below for more information about migrating from the beta interface to GA.
Beta header

For REST API requests, WebSocket connections, and other interfaces with the Realtime API, beta users had to include the following header with each request:

OpenAI-Beta: realtime=v1

This header should be removed for requests to the GA interface. To retain the behavior of the beta API, you should continue to include this header.
Generating ephemeral API keys

In the beta interface, there were multiple endpoints for generating ephemeral keys for either Realtime sessions or transcription sessions. In the GA interface, there is only one REST API endpoint used to generate keys - [POST /v1/realtime/client_secrets](http...

• Fixes Redo: https://github.com/hack-r/realtime-hud/pull/3 #4

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.