OpenAI SDK-compatible realtime transcription and speech-to-speech

import { once } from "node:events";import { readFile } from "node:fs/promises";import OpenAI from "openai";import { OpenAIRealtimeWebSocket } from "openai/realtime/websocket";const client = new OpenAI({  apiKey: process.env.ALLMODELS_API_KEY,  baseURL: "https://api.allmodels.io/oai"});const realtime = await OpenAIRealtimeWebSocket.create(client, {  model: "openai/gpt-realtime-whisper"});realtime.on("conversation.item.input_audio_transcription.delta", ({ delta }) => console.log(delta));realtime.on("conversation.item.input_audio_transcription.completed", ({ transcript }) => {  console.log(transcript);  realtime.close({ code: 1000, reason: "complete" });});if (realtime.socket.readyState !== 1) await once(realtime.socket, "open");realtime.send({ type: "session.update", session: {  type: "transcription",  audio: { input: { format: { type: "audio/pcm", rate: 24000 }, transcription: { model: "openai/gpt-realtime-whisper", language: "en" }, turn_detection: null } }}});realtime.send({ type: "input_audio_buffer.append", audio: (await readFile("chunk.pcm")).toString("base64") });realtime.send({ type: "input_audio_buffer.commit" });

import asyncioimport base64import osfrom pathlib import Pathfrom openai import AsyncOpenAIasync def main():    client = AsyncOpenAI(        api_key=os.environ["ALLMODELS_API_KEY"],        base_url="https://api.allmodels.io/oai",    )    async with client.realtime.connect(        model="openai/gpt-realtime-whisper",        extra_query={"intent": "transcription"},    ) as connection:        await connection.session.update(session={            "type": "transcription",            "audio": {"input": {"format": {"type": "audio/pcm", "rate": 24000}, "transcription": {"model": "openai/gpt-realtime-whisper", "language": "en"}, "turn_detection": None}},        })        audio = base64.b64encode(Path("chunk.pcm").read_bytes()).decode("ascii")        await connection.input_audio_buffer.append(audio=audio)        await connection.input_audio_buffer.commit()        async for event in connection:            if event.type.endswith(("transcription.delta", "transcription.completed")):                print(event)            if event.type == "conversation.item.input_audio_transcription.completed":                breakasyncio.run(main())