Quickstart

import asyncio, base64, json, os, wave

import websockets

URL = "wss://api.eesi.ai/v1/realtime?model=nur-v1"
KEY = os.environ["EESI_API_KEY"]
VOICE = os.environ["VOICE"]


async def main(question_wav: str) -> None:
    # The question must be 16 kHz, mono, 16-bit PCM WAV.
    with wave.open(question_wav) as clip:
        pcm = clip.readframes(clip.getnframes())

    async with websockets.connect(
        URL, additional_headers={"Authorization": f"Bearer {KEY}"}
    ) as ws:
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "type": "realtime",
                "instructions": "You are a friendly guide. Keep answers short.",
                "audio": {
                    "output": {
                        "voice": VOICE,
                        "format": {"type": "audio/pcm", "rate": 24000},
                    }
                },
            },
        }))

        async def speak() -> None:
            # 20 ms per message, paced like a live microphone, then silence
            # so Nur hears that you stopped.
            chunk = 640
            for start in range(0, len(pcm), chunk):
                await ws.send(json.dumps({
                    "type": "input_audio_buffer.append",
                    "audio": base64.b64encode(pcm[start:start + chunk]).decode(),
                }))
                await asyncio.sleep(0.02)
            silence = base64.b64encode(bytes(chunk)).decode()
            for _ in range(75):
                await ws.send(json.dumps({"type": "input_audio_buffer.append", "audio": silence}))
                await asyncio.sleep(0.02)

        asyncio.create_task(speak())
        reply = bytearray()
        async for raw in ws:
            event = json.loads(raw)
            if event["type"] == "response.output_audio.delta":
                reply += base64.b64decode(event["delta"])
            elif event["type"] == "response.output_audio_transcript.delta":
                print(event["delta"], end="", flush=True)
            elif event["type"] == "response.done" and reply:
                break
            elif event["type"] == "error":
                print("\nerror:", event["error"]["message"])

    with wave.open("reply.wav", "wb") as out:
        out.setnchannels(1)
        out.setsampwidth(2)
        out.setframerate(24000)
        out.writeframes(bytes(reply))
    print("\nSaved reply.wav")


asyncio.run(main("question.wav"))