Integration with Twilio

[oemd001]

Hello!
I am currently using Twilio as my method to make phone calls + streaming the voice data to my server.
However, when I tried to convert Twilio's x-mulaw audio format to PCM Linear (as expected from WhisperLive), I don't get any response from WhisperLive. In other words, I know that my GPU is working, I know that the audio data works (I converted the audio to a wav file and listened to it clearly) but I'm not getting any transcription.

I also thought it was worth noting that the audio was a bit quiet--not sure if that could be a source of suspicion?

Here's my code conversion (from x-mulaw to PCM)

audio = base64.b64decode(packet['media']['payload'])
audio = audioop.ulaw2lin(audio, 2)
audio = audioop.ratecv(audio, 2, 1, 8000, 16000, None)[0]
await websocket.send(audio)

Let me know if you'd like me to provide any additional context :)
Thanks for the help in advance!

[arkadiy-telegin]

same issue:

pcm_bytes = audioop.ulaw2lin(chunk, 2)
        pcm_upsampled, _ = audioop.ratecv(pcm_bytes, 2, 1, 8000, 16000, None)
        pcm_array = np.frombuffer(pcm_bytes, dtype=np.int16)
        pcm_float32 = pcm_array.astype(np.float32) / 32768.0
        to_buffer = pcm_float32.tobytes()

Can't get this to work