تحويل الكلام إلى نص في الوقت الحقيقي

# pip install websockets pyaudio
import asyncio
import websockets
import json
import pyaudio
import sys

API_KEY = "YOUR_API_KEY"
URL = "wss://moknah.io/api/v1/stt/ws/?language=ar-SA"

# 16kHz, 16-bit, Mono (100ms chunks)
CHUNK = 1600

async def stream_live_microphone(ws):
    audio = pyaudio.PyAudio()
    stream = audio.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True, frames_per_buffer=CHUNK)

    print("🎤 Microphone is LIVE. Start speaking!")
    loop = asyncio.get_running_loop()

    try:
        while True:
            data = await loop.run_in_executor(None, stream.read, CHUNK, False)
            await ws.send(data)
            await asyncio.sleep(0.001)
    except asyncio.CancelledError:
        await ws.send(json.dumps({"command": "stop"}))
    finally:
        stream.stop_stream()
        stream.close()
        audio.terminate()

async def receive_transcriptions(ws):
    async for message in ws:
        data = json.loads(message)
        if data.get('type') == 'partial':
            sys.stdout.write(f"\r⏳ {data['text']}")
            sys.stdout.flush()
        elif data.get('type') == 'final':
            sys.stdout.write(f"\r✅ {data['text']}\n")
            sys.stdout.flush()

async def main():
    headers = {"Authorization": f"Bearer {API_KEY}"}
    async with websockets.connect(URL, additional_headers=headers) as ws:
        await asyncio.gather(
            asyncio.create_task(stream_live_microphone(ws)),
            asyncio.create_task(receive_transcriptions(ws))
        )

asyncio.run(main())