Skip to content

Commit c8e0648

Browse files
kathaylkodster28jhutchings1
authored andcommitted
Create 2025-03-20-websockets.mdx (#21003)
* Create 2025-03-20-websockets.mdx * Update 2025-03-20-websockets.mdx wording changes * Apply suggestions from code review * Update src/content/changelog/ai-gateway/2025-03-20-websockets.mdx Co-authored-by: Justin Hutchings <[email protected]> * Update 2025-03-20-websockets.mdx update date --------- Co-authored-by: Kody Jackson <[email protected]> Co-authored-by: Justin Hutchings <[email protected]>
1 parent 293177d commit c8e0648

File tree

1 file changed

+37
-0
lines changed

1 file changed

+37
-0
lines changed
Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
---
2+
title: AI Gateway launches Realtime WebSockets API
3+
description: AI Gateway now supports end-to-end, client-to-provider WebSockets
4+
date: 2025-03-21T09:00:00Z
5+
---
6+
We are excited to announce that [AI Gateway](/ai-gateway/) now supports real-time AI interactions with the new [Realtime WebSockets API](/ai-gateway/configuration/websockets-api/realtime-api/).
7+
8+
This new capability allows developers to establish persistent, low-latency connections between their applications and AI models, enabling natural, real-time conversational AI experiences, including speech-to-speech interactions.
9+
10+
The Realtime WebSockets API works with the [OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime#connect-with-websockets), [Google Gemini Live API](https://ai.google.dev/gemini-api/docs/multimodal-live), and supports real-time text and speech interactions with models from [Cartesia](https://docs.cartesia.ai/api-reference/tts/tts), and [ElevenLabs](https://elevenlabs.io/docs/conversational-ai/api-reference/conversational-ai/websocket).
11+
12+
Here's how you can connect AI Gateway to [OpenAI's Realtime API](https://platform.openai.com/docs/guides/realtime#connect-with-websockets) using WebSockets:
13+
```javascript title="OpenAI Realtime API example"
14+
import WebSocket from "ws";
15+
16+
const url =
17+
"wss://gateway.ai.cloudflare.com/v1/<account_id>/<gateway>/openai?model=gpt-4o-realtime-preview-2024-12-17";
18+
const ws = new WebSocket(url, {
19+
headers: {
20+
"cf-aig-authorization": process.env.CLOUDFLARE_API_KEY,
21+
Authorization: "Bearer " + process.env.OPENAI_API_KEY,
22+
"OpenAI-Beta": "realtime=v1",
23+
},
24+
});
25+
26+
ws.on("open", () => console.log("Connected to server."));
27+
ws.on("message", (message) => console.log(JSON.parse(message.toString())));
28+
29+
ws.send(
30+
JSON.stringify({
31+
type: "response.create",
32+
response: { modalities: ["text"], instructions: "Tell me a joke" },
33+
}),
34+
);
35+
```
36+
37+
Get started by checking out the [Realtime WebSockets API](/ai-gateway/configuration/websockets-api/realtime-api/) documentation.

0 commit comments

Comments
 (0)