صدا، زنده و دوطرفه

curl -X POST https://1xai.ir/v1/realtime/client_secret \
  -H "Authorization: Bearer $ONEXAI_API_KEY"

# {
#   "client_secret": { "value": "ek_...", "expires_at": 1756240000 },
#   "model": "gpt-realtime",
#   "url":   "wss://1xai.ir/rt/voice"
# }

# Your backend. The API key lives here and only here.
import httpx
from fastapi import FastAPI

app = FastAPI()

@app.post("/voice-token")
async def voice_token():
    async with httpx.AsyncClient() as http:
        r = await http.post(
            "https://1xai.ir/v1/realtime/client_secret",
            headers={"Authorization": f"Bearer {ONEXAI_API_KEY}"},
        )
    r.raise_for_status()
    return r.json()   # hand straight to your front end

// Your page. Never sees the API key.
const { client_secret, url } = await fetch("/voice-token", { method: "POST" })
  .then((r) => r.json());

const ws = new WebSocket(`${url}?client_secret=${client_secret.value}`);

ws.onopen = () => {
  // Configure the session: voice, Persian transcription, turn detection.
  ws.send(JSON.stringify({
    type: "session.update",
    session: {
      instructions: "به فارسی و کوتاه پاسخ بده.",
      audio: {
        input: {
          format: "pcm16",
          transcription: { model: "whisper-1", language: "fa" },
          // Server-side VAD: the model decides when you stopped talking,
          // and interrupting it cancels its reply (barge-in).
          turn_detection: { type: "server_vad", interrupt_response: true },
        },
        output: { format: "pcm16", voice: "alloy" },
      },
      tools: [{
        type: "function",
        name: "lookup_order",
        description: "Look up an order in the ERP",
        parameters: {
          type: "object",
          properties: { id: { type: "string" } },
          required: ["id"],
        },
      }],
    },
  }));
};

ws.onmessage = (e) => {
  const ev = JSON.parse(e.data);
  switch (ev.type) {
    case "conversation.item.input_audio_transcription.completed":
      console.log("user said:", ev.transcript);          // live transcript
      break;
    case "response.output_audio.delta":
      playPCM(atob(ev.delta));                            // model speaking
      break;
    case "response.function_call_arguments.done":
      callYourERP(ev.name, JSON.parse(ev.arguments));     // function calling
      break;
    case "error":
      // insufficient_funds arrives here before the socket closes
      console.error(ev.error);
      break;
  }
};

// Microphone in: base64 PCM16 frames, as they are captured.
function sendMic(pcm16) {
  ws.send(JSON.stringify({ type: "input_audio_buffer.append", audio: pcm16 }));
}

// Server-side client (no browser). Header instead of query string —
// query strings reach access logs, headers do not.
import WebSocket from "ws";

const ws = new WebSocket("wss://1xai.ir/rt/voice", {
  headers: { Authorization: `Bearer ${clientSecret}` },
});