Stream speech to text

import asyncio
import json
import wave

import websockets  # pip install "websockets>=14"

URL = "wss://api.echonova.ai/v1/speech-to-text/stream"
API_KEY = "YOUR_API_KEY"


async def main():
    # A 16-bit mono PCM WAV file; its header gives the sample rate.
    with wave.open("audio.wav", "rb") as wav:
        if wav.getsampwidth() != 2 or wav.getnchannels() != 1:
            raise SystemExit("audio.wav must be 16-bit mono PCM")
        rate = wav.getframerate()
        pcm = wav.readframes(wav.getnframes())

    async with websockets.connect(
        f"{URL}?sample_rate={rate}&language=ar",
        additional_headers={"Authorization": f"Bearer {API_KEY}"},
    ) as ws:
        print(json.loads(await ws.recv()))  # session.started

        async def send_audio():
            step = rate // 10 * 2  # 100 ms of 16-bit samples, in bytes
            for i in range(0, len(pcm), step):
                await ws.send(pcm[i : i + step])  # bytes: a binary frame
                await asyncio.sleep(0.1)  # real time, like a live source
            await ws.send(json.dumps({"type": "end_segment"}))
            await ws.send(json.dumps({"type": "stop"}))

        sender = asyncio.create_task(send_audio())
        async for raw in ws:  # ends when the server closes after session.ended
            message = json.loads(raw)
            if message["type"] == "transcript":
                print(message["text"])
            elif message["type"] == "error":
                print("error:", message["code"], message["message"])
            elif message["type"] == "session.ended":
                print("ended:", message["reason"], "credits:", message["creditsConsumed"])
        await sender


asyncio.run(main())