I m trying to transcribe audio to text using Google Speech to Text using Python. For this I m using the websocket stream to receive the audio.

@app.route("/receive_call", methods=['GET', 'POST'])
def receive_call():
    if request.method == 'POST':
        xml = f"""
<Response>
    <Say>
        Speak to see your speech transcribed in the console
    </Say>
    <Connect>
        <Stream url='wss://{request.host}{WEBSOCKET_ROUTE}' />
    </Connect>
</Response>
""".strip()

        return Response(xml, mimetype='text/xml')
    else:
        return f"Real-time phone call transcription app"

Here the websocket Code:

@sock.route(WEBSOCKET_ROUTE)
def transcription_websocket(ws):
    # audio_generator(ws)
    while True:

        data = json.loads(ws.receive())
        match data['event']:
            case "connected":
                transcriber = TwilioTranscriber()
                transcriber.connect()
                print('transcriber connected')
            case "start":
                print('twilio started')
            case "media":
                payload_b64 = data['media']['payload']
                chunk = base64.b64decode(payload_b64)
                transcribe=transcribe_audio(chunk)
                print(transcribe) 

The above value is returned as None.

So far I have tried to transcribe the audio using Google Speech to Text Api. Tried with the MULAW or Linear Encoding but getting the None as output.
Tried with
**Encoding ** : MULAW or Linear16
sample rate: 8000 or 16000
None of the above is working.

def transcribe_audio(audio_content):
    client = speech.SpeechClient()
    audio = speech.RecognitionAudio(content=audio_content)
    config = speech.RecognitionConfig(
        encoding="MULAW",
        sample_rate_hertz=8000,
        language_code="en-US" )

    response = client.recognize(config=config, audio=audio)
    for result in response.results:
        return result.alternatives[0].transcript

Note: Using Ngrok to run the websocket locally