Голосовой режим реального времени (WebSocket)

{
  "type": "session.update",
  "session": {
    "modalities": ["text", "audio"],
    "voice": "Ethan",
    "input_audio_format": "pcm",
    "output_audio_format": "pcm",
    "input_audio_transcription": { "model": "qwen3-asr-flash-realtime" },
    "turn_detection": { "type": "semantic_vad" }
  }
}

{
  "type": "session.update",
  "session": {
    "type": "realtime",
    "output_modalities": ["audio"],
    "audio": {
      "input": {
        "format": { "type": "audio/pcm", "rate": 24000 },
        "transcription": { "model": "whisper-1" },
        "turn_detection": { "type": "semantic_vad" }
      },
      "output": {
        "format": { "type": "audio/pcm", "rate": 24000 },
        "voice": "alloy",
        "speed": 1.0
      }
    }
  }
}

import asyncio, json, os, websockets

FAMILY = "ga"           # ga = gpt-realtime-2.1 series; omni = qwen3.5-omni series
MODEL = "gpt-realtime-2.1" if FAMILY == "ga" else "qwen3.5-omni-plus-realtime"
URL = f"wss://api.apiyi.com/v1/realtime?model={MODEL}"
HEADERS = {"Authorization": "Bearer " + os.environ["APIYI_API_KEY"]}

# The two protocols diverge only here: session structure and the text-delta event name.
SESSION = ({"type": "realtime", "output_modalities": ["text"],
            "audio": {"input": {"turn_detection": None}}}
           if FAMILY == "ga" else
           {"modalities": ["text"], "turn_detection": None})
TEXT_DELTA = "response.output_text.delta" if FAMILY == "ga" else "response.text.delta"

async def main():
    async with websockets.connect(URL, additional_headers=HEADERS) as ws:
        while json.loads(await ws.recv())["type"] != "session.created":
            pass
        await ws.send(json.dumps({"type": "session.update", "session": SESSION}))
        await ws.send(json.dumps({"type": "conversation.item.create", "item": {
            "type": "message", "role": "user",
            "content": [{"type": "input_text", "text": "Explain WebSocket in one sentence."}]}}))
        await ws.send(json.dumps({"type": "response.create"}))
        while True:
            e = json.loads(await ws.recv())
            if e["type"] == TEXT_DELTA:
                print(e["delta"], end="", flush=True)
            elif e["type"] == "response.done":
                print("\n\nusage =", json.dumps(e["response"]["usage"]))
                return
            elif e["type"] == "error":
                print("\nERROR:", json.dumps(e))
                return

asyncio.run(main())

{
  "type": "conversation.item.create",
  "item": {
    "type": "function_call_output",
    "call_id": "call_xxx",
    "output": "{\"city\":\"Beijing\",\"weather\":\"light rain\",\"temp_c\":21}"
  }
}

{
  "type": "conversation.item.create",
  "item": {
    "type": "message",
    "role": "user",
    "content": [
      { "type": "input_image", "image_url": "data:image/jpeg;base64,..." },
      { "type": "input_text", "text": "What does the image say?" }
    ]
  }
}