Search

Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to create a fresh table.
### OpenAI
```ts
import { OpenAI } from "https://esm.town/v/std/openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
  messages: [
    { role: "user", content: "Say hello in a creative way" },

const REALTIME_BASE_URL = "https://api.openai.com/v1/realtime";
const OPENAI_API_KEY = Deno.env.get("OPENAI_API_KEY");
if (!OPENAI_API_KEY) {
  throw new Error("🔴 OpenAI API key not configured");
}
export function makeHeaders(contentType?: string) {
  const obj: Record<string, string> = {
    Authorization: `Bearer ${OPENAI_API_KEY}`,
  };
  if (contentType) obj["Content-Type"] = contentType;

sip.post("/", async (c) => {
  // Verify the webhook.
  const OPENAI_SIGNING_SECRET = Deno.env.get("OPENAI_SIGNING_SECRET");
  if (!OPENAI_SIGNING_SECRET) {
    console.error("🔴 webhook secret not configured");
    return c.text("Internal error", 500);
  }
  const webhook = new Webhook(OPENAI_SIGNING_SECRET);
  const bodyStr = await c.req.text();
  let callId: string | undefined;

# hello-realtime
**Hello Realtime** is a OpenAI Realtime app that supports both WebRTC and SIP
(telephone) users. You can access the app via WebRTC at
[hello-realtime.val.run](https://hello-realtime.val.run), or via SIP by calling
server-side websocket interface.
If you remix the app, you'll just need to pop in your own `OPENAI_API_KEY` (from
[platform.openai.com](https://platform.openai.com)), and if you want SIP, the
`OPENAI_SIGNING_SECRET`.
## Architecture
   - Browser connects to frontend
   - creates WebRTC offer
   - `/rtc` endpoint handles SDP negotiation with OpenAI
   - observer established to monitor session
2. **SIP Flow**:

    <meta charset="utf-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1" />
    <title>OpenAI Realtime API Voice Agent</title>
    <style>
      :root {

const NR_TYPE = "near_field";
const INSTRUCTIONS = `
  Greet the user in English and tell them that they're using the OpenAI Realtime API, powered by the {{model}} model.
  Give them a very brief summary of the benefits of the Realtime API based on the headline below,
  and then ask if they have any questions.
  - higher audio quality
  - improved handling of alphanumerics (eg, properly understanding credit card and phone numbers)
  - support for the OpenAI Prompts API
  - support for MCP-based tools
  - auto-truncation to reduce context size

import { streamText } from "npm:hono@4.4.12/streaming";
import type { Context } from "npm:hono@4.4.12";
import { OpenAI } from "https://esm.town/v/std/openai";
import { nanoid } from "npm:nanoid";
// --- CORE AI & HELPER LOGIC ---
const openai = new OpenAI();
const services = {
  async callAI(
      if (isJson) requestPayload.response_format = { type: "json_object" };
      const completion = await openai.chat.completions.create(requestPayload);
      const content = completion.choices?.[0]?.message?.content ?? "";
    onDelta: (delta: string) => Promise<void>,
  ) {
    const completionStream = await openai.chat.completions.create({
      model: "gpt-4o",
      messages: [{ role: "system", content: systemPrompt }, {

## Other todos
- [ ] Get OpenTownie or Gemini or Claude or OpenAI to synthesize the core of these patterns into a prompt we can use to make more ReactRouter apps, such as...
- [ ] Convert this or into the basic react router guest book (and preserve this forum app in another project?)
- [ ] To what extent can these patterns be packaged up into a Val Town Router project? Would be neat to get the version pinning thing all centralized, can this as-a-library be that centralized place?

// @ts-ignore
import { OpenAI } from "https://esm.town/v/std/openai?v=4";
// --- AI BEHAVIORAL GUIDELINES ---
async function handleApiDispatch(req: Request): Promise<Response> {
  try {
    const openai = new OpenAI();
    const body = await req.json();
    }`;
    const completion = await openai.chat.completions.create({
      model: "gpt-4o", // Using a powerful model for complex logic
      messages: [

Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to create a fresh table.
### OpenAI
```ts
import { OpenAI } from "https://esm.town/v/std/openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
  messages: [
    { role: "user", content: "Say hello in a creative way" },