python_to_deepgram.py

import base64
import json
import websockets
import asyncio
import os
import pyaudio
import sys
import logging

FRAMES_PER_BUFFER = 3200
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000

audio_client = pyaudio.PyAudio()


stream_in = audio_client.open(
    format=FORMAT,
    channels=CHANNELS,
    rate=RATE,
    input=True,
    input_device_index=1,
    frames_per_buffer=FRAMES_PER_BUFFER,
)

print("stream started")

loghandler = logging.StreamHandler(sys.stdout)
logging.basicConfig(level=logging.DEBUG, handlers=[loghandler])


def connect():
    """Connect to the websocket endpoint."""
    return websockets.connect(
        ## Connect to the secure websocket endpoint.
        "wss://api.deepgram.com/v1/listen",
        extra_headers={
            "Authorization": "Token {}".format(os.getenv("DEEPGRAM_API_KEY"))
        },
        ping_interval=5
    )


async def run():
    """Streams data to/from the service.

    We will use `key` to authenticate.
    We will read audio data from the `outbox` queue and send it to the server.
    When we receive responses from the server, we will put the latest transcript in the `inbox` queue.
    """
    async with connect() as ws:
        print("Websocket connection initialised")

        async def sender(ws):
            while True:
                try:
                    input_audio = stream_in.read(3200)
                    # input_audio = base64.b64encode(input_audio).decode("utf-8")
                    await ws.send(input_audio)
                    await asyncio.sleep(0)
                except Exception as e:
                    print(e)
                except websockets.ConnectionClosed:
                    print("connection closed")
                    
            await ws.send(b'')

        async def receiver(ws):
            async for msg in ws:
                # while True:
                print("receiving something..")
                # msg = await ws.recv()
                print(msg)

                msg = json.loads(msg)

                if "alternatives" in msg:
                    transcript = msg["alternatives"][0]["transcript"]
                    print("Metadata received:", msg)
                    print(f"transcript from alternatives - {transcript}")

                elif "channel" in msg and msg["is_final"]:
                    transcript = msg["channel"]["alternatives"][0]["transcript"]
                    print("Metadata received:", msg)
                    print(f"transcript channel - {transcript}")

                else:
                    print("Metadata received:", msg)

        # send_result, receive_result = await asyncio.gather(sender(), receiver())
        await asyncio.wait(
            [asyncio.ensure_future(sender(ws)), asyncio.ensure_future(receiver(ws))]
        )


if __name__ == "__main__":
    asyncio.run(run())
    asyncio.get_event_loop().run_forever()