GPT Realtime Whisper

import asyncio, json, websockets

URL = "wss://synthorai.io/v1/realtime?model=gpt-realtime-2.1"
# Send ONLY the Authorization header - the beta protocol is retired.
HEADERS = {"Authorization": "Bearer sk-syn-..."}

async def main():
    async with websockets.connect(URL, additional_headers=HEADERS) as ws:
        # 1) name gpt-realtime-whisper as the session's input transcription model
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "type": "realtime",
                "audio": {"input": {"transcription": {"model": "gpt-realtime-whisper"}}},
            },
        }))
        # 2) send input audio (base64 PCM16) and commit it
        await ws.send(json.dumps({"type": "input_audio_buffer.append", "audio": pcm16_b64}))
        await ws.send(json.dumps({"type": "input_audio_buffer.commit"}))
        # 3) the transcript of what was said arrives as its own event
        async for raw in ws:
            ev = json.loads(raw)
            if ev["type"] == "conversation.item.input_audio_transcription.completed":
                print(ev["transcript"])
                break

asyncio.run(main())

import WebSocket from "ws";

const ws = new WebSocket("wss://synthorai.io/v1/realtime?model=gpt-realtime-2.1", {
  // Send ONLY the Authorization header, the beta protocol is retired.
  headers: { Authorization: "Bearer sk-syn-..." },
});

ws.on("open", () => {
  // name gpt-realtime-whisper as the session's input transcription model
  ws.send(JSON.stringify({ type: "session.update", session: {
    type: "realtime", audio: { input: { transcription: { model: "gpt-realtime-whisper" } } },
  } }));
  // send input audio (base64 PCM16) and commit it
  ws.send(JSON.stringify({ type: "input_audio_buffer.append", audio: pcm16Base64 }));
  ws.send(JSON.stringify({ type: "input_audio_buffer.commit" }));
});

ws.on("message", (raw) => {
  const ev = JSON.parse(raw.toString());
  if (ev.type === "conversation.item.input_audio_transcription.completed") {
    console.log(ev.transcript); // the transcript of what was said
    ws.close();
  }
});

# Realtime is a WebSocket protocol - use a WS client such as websocat.
# Each line below is one OpenAI Realtime event (JSON) sent to the session.
websocat -H 'Authorization: Bearer sk-syn-...' \
  'wss://synthorai.io/v1/realtime?model=gpt-realtime-2.1' <<'EOF'
{"type":"session.update","session":{"type":"realtime","audio":{"input":{"transcription":{"model":"gpt-realtime-whisper"}}}}}
{"type":"input_audio_buffer.append","audio":"<base64-pcm16>"}
{"type":"input_audio_buffer.commit"}
EOF
# The transcript arrives as conversation.item.input_audio_transcription.completed

package main

import (
	"fmt"
	"net/http"

	"github.com/gorilla/websocket"
)

func main() {
	h := http.Header{}
	h.Set("Authorization", "Bearer sk-syn-...")
	// Send ONLY the Authorization header, the beta protocol is retired.
	c, _, err := websocket.DefaultDialer.Dial("wss://synthorai.io/v1/realtime?model=gpt-realtime-2.1", h)
	if err != nil {
		panic(err)
	}
	defer c.Close()

	// name gpt-realtime-whisper as the session's input transcription model, then send audio
	c.WriteJSON(map[string]any{"type": "session.update", "session": map[string]any{
		"type": "realtime",
		"audio": map[string]any{"input": map[string]any{
			"transcription": map[string]any{"model": "gpt-realtime-whisper"}}}}})
	c.WriteJSON(map[string]any{"type": "input_audio_buffer.append", "audio": pcm16B64})
	c.WriteJSON(map[string]any{"type": "input_audio_buffer.commit"})

	for {
		var ev struct {
			Type       string `json:"type"`
			Transcript string `json:"transcript"`
		}
		if err := c.ReadJSON(&ev); err != nil {
			return
		}
		if ev.Type == "conversation.item.input_audio_transcription.completed" {
			fmt.Println(ev.Transcript) // the transcript of what was said
			return
		}
	}
}

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.WebSocket;
import java.util.concurrent.CompletionStage;

// JDK built-in WebSocket, no extra dependency needed.
WebSocket ws = HttpClient.newHttpClient().newWebSocketBuilder()
    .header("Authorization", "Bearer sk-syn-...")
    // Send ONLY the Authorization header, the beta protocol is retired.
    .buildAsync(URI.create("wss://synthorai.io/v1/realtime?model=gpt-realtime-2.1"), new WebSocket.Listener() {
        public CompletionStage<?> onText(WebSocket w, CharSequence data, boolean last) {
            // conversation.item.input_audio_transcription.completed carries the transcript
            w.request(1);
            return null;
        }
    }).join();

// name gpt-realtime-whisper as the session's input transcription model, then send audio
ws.sendText("{\"type\":\"session.update\",\"session\":{\"type\":\"realtime\",\"audio\":{\"input\":{\"transcription\":{\"model\":\"gpt-realtime-whisper\"}}}}}", true);
ws.sendText("{\"type\":\"input_audio_buffer.append\",\"audio\":\"<base64-pcm16>\"}", true);
ws.sendText("{\"type\":\"input_audio_buffer.commit\"}", true);