Realtime Conversation

# Dependency: pip install "openai[realtime]"
import asyncio
import base64
from openai import AsyncOpenAI

# Reusing the official SDK requires only two adaptations:
#   1) point websocket_base_url at the AiHubMix gateway (instead of OpenAI's default address)
#   2) pass model explicitly to connect(), required for the gateway handshake (the conversation endpoint needs no intent)
client = AsyncOpenAI(
    api_key="sk-***",  # Replace with your AiHubMix API key
    websocket_base_url="wss://aihubmix.com/v1",
)

async def main():
    async with client.realtime.connect(model="gpt-realtime-2.1") as conn:
        # 1) Configure the session: system instructions + voice + VAD (automatic turn detection)
        await conn.session.update(session={
            "type": "realtime",
            "instructions": "You are a helpful voice assistant. Keep answers concise.",
            "audio": {
                "input": {
                    "format": {"type": "audio/pcm", "rate": 24000},
                    "turn_detection": {"type": "server_vad"},
                },
                "output": {
                    "format": {"type": "audio/pcm", "rate": 24000},
                    "voice": "alloy",
                },
            },
        })

        # 2) Send a text message and request a reply (for audio input see append/commit in the raw example)
        await conn.conversation.item.create(item={
            "type": "message",
            "role": "user",
            "content": [{"type": "input_text", "text": "What is the capital of France?"}],
        })
        await conn.response.create()

        # 3) Receive this turn's reply: text arrives as transcript deltas, speech as audio deltas
        async for event in conn:
            if event.type == "response.output_audio_transcript.delta":
                print(event.delta, end="", flush=True)  # reply text (when output includes audio)
            elif event.type == "response.output_audio_transcript.done":
                print()  # this turn's transcript finished
            elif event.type == "response.output_text.delta":
                print(event.delta, end="", flush=True)  # text-only output
            elif event.type == "response.output_text.done":
                print()
            elif event.type == "response.output_audio.delta":
                pass  # base64 PCM16 audio chunk, decode to play
            elif event.type == "input_audio_buffer.speech_started":
                pass  # user interruption: stop playback, then call conn.conversation.item.truncate(...)
            elif event.type == "response.done":
                print("\n[turn complete]", event.response.usage)
                break
            elif event.type == "error":
                print("\n[error]", event.to_dict())
                break

asyncio.run(main())

import asyncio
import base64
import json
import websockets

API_KEY = "sk-***"  # Replace with your AiHubMix API key
URL = "wss://aihubmix.com/v1/realtime?model=gpt-realtime-2.1"

async def main():
    # websockets >= 13 uses additional_headers; older versions use extra_headers
    async with websockets.connect(
        URL, additional_headers={"Authorization": f"Bearer {API_KEY}"}
    ) as ws:
        # 1) Configure the session (VAD off, control the reply timing manually)
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "type": "realtime",
                "instructions": "You are a helpful voice assistant.",
                "audio": {
                    "input": {
                        "format": {"type": "audio/pcm", "rate": 24000},
                        "turn_detection": None,
                    },
                    "output": {
                        "format": {"type": "audio/pcm", "rate": 24000},
                        "voice": "alloy",
                    },
                },
            },
        }))

        # 2) Read a local raw PCM16 / 24kHz / mono file, send it in chunks, then commit + request a reply
        async def send_audio():
            with open("audio_pcm16_24k.raw", "rb") as f:
                pcm = f.read()
            chunk = 24000 * 2 // 10  # 100ms = sample rate x 2 bytes / 10
            for i in range(0, len(pcm), chunk):
                await ws.send(json.dumps({
                    "type": "input_audio_buffer.append",
                    "audio": base64.b64encode(pcm[i:i + chunk]).decode(),
                }))
                await asyncio.sleep(0.1)  # simulate realtime pacing
            # With VAD off, commit and request a reply manually
            await ws.send(json.dumps({"type": "input_audio_buffer.commit"}))
            await ws.send(json.dumps({"type": "response.create"}))

        asyncio.create_task(send_audio())

        # 3) Receive the reply
        async for msg in ws:
            evt = json.loads(msg)
            etype = evt.get("type", "")
            if etype == "response.output_audio_transcript.delta":
                print(evt.get("delta", ""), end="", flush=True)  # reply text (when output includes audio)
            elif etype == "response.output_audio_transcript.done":
                print()  # this turn's transcript finished
            elif etype == "response.output_text.delta":
                print(evt.get("delta", ""), end="", flush=True)  # text-only output
            elif etype == "input_audio_buffer.speech_started":
                pass  # user interruption: stop playback, then send conversation.item.truncate
            elif etype == "response.output_audio.delta":
                pass  # base64 PCM16 audio chunk, decode to play
            elif etype == "response.done":
                print("\n[turn complete]", evt.get("response", {}).get("usage"))
                break
            elif etype == "error":
                print("\n[error]", evt.get("error"))
                break

asyncio.run(main())

# Dependency: pip install openai-agents
import asyncio
from agents.realtime import (
    OpenAIRealtimeWebSocketModel,
    RealtimeAgent,
    RealtimeSession,
)

agent = RealtimeAgent(
    name="Assistant",
    instructions="You are a helpful voice assistant. Keep answers concise.",
)

async def main():
    session = RealtimeSession(
        OpenAIRealtimeWebSocketModel(),
        agent,
        None,
        model_config={
            "api_key": "sk-***",  # Replace with your AiHubMix API key
            "url": "wss://aihubmix.com/v1/realtime?model=gpt-realtime-2.1",
        },
        run_config={
            "model_settings": {
                "modalities": ["audio"],
                "output_audio_format": "pcm16",
                # Must disable: the input audio transcription this API does not support,
                # and leaving it on gets the session closed with 1008
                "input_audio_transcription": None,
            },
        },
    )
    async with session:
        await session.send_message("What is the capital of France?")
        async for event in session:
            if getattr(event, "type", "") == "raw_model_event":
                data = getattr(event, "data", None)
                if getattr(data, "type", "") == "transcript_delta":
                    print(getattr(data, "delta", ""), end="", flush=True)
                elif getattr(data, "type", "") == "turn_ended":
                    print("\n[turn complete]")
                    return

asyncio.run(main())

# Use wscat to quickly verify connectivity and authentication (requires npm i -g wscat)
wscat -c "wss://aihubmix.com/v1/realtime?model=gpt-realtime-2.1" \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY"

# Once connected, paste a session.update frame, then send a text message + response.create to start