error python audio

[codiac]

this is my code:

import os
import pyaudio
import openai
import soundfile as sf
import numpy as np
import base64
from pydub import AudioSegment
from pydub.utils import which, mediainfo, make_chunks, silence
from pydub.silence import detect_nonsilent

# set up OpenAI API key
openai.api_key = "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"

# set up audio stream
CHUNK = 2000
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 3000

p = pyaudio.PyAudio()

stream = p.open(format=FORMAT,
                channels=CHANNELS,
                rate=RATE,
                input=True,
                frames_per_buffer=CHUNK)

# set up prompt
prompt = "Hello, how can I help you today?"

# check if ffmpeg exists in the system path or the pydub package can find it
if which("ffmpeg") is None:
    os.environ["PATH"] += os.pathsep + "/usr/local/bin/ffmpeg"

while True:
    # record audio from microphone
    frames = []
    for i in range(int(RATE / CHUNK * 5)):
        data = stream.read(CHUNK)
        frames.append(data)

    # convert audio to text using OpenAI API
    audio_data = b''.join(frames)
    audio_array = np.frombuffer(audio_data, dtype=np.int16)
    sf.write("input.wav", audio_array, RATE)

    audio = AudioSegment.from_wav("input.wav")

    try:
        audio.export("input.mp3", format="mp3", codec="libmp3lame")

        with open("input.mp3", "rb") as f:
            audio_bytes = f.read()

        # encode audio bytes as base64 string
        audio_base64 = base64.b64encode(audio_bytes).decode()

        response = openai.Completion.create(
            engine="davinci",
            prompt=prompt,
            audio=audio_base64,
            temperature=0.5,
            max_tokens=60,
            n=1,
            stop=None,
            timeout=10,
        )

        if "choices" in response and len(response["choices"]) > 0:
            response_audio_base64 = response["choices"][0]["audio"]
            response_audio = base64.b64decode(response_audio_base64)

            # detect silence in response audio and remove it
            response_audio = AudioSegment.from_file(
                response_audio, format="mp3")
            non_silent_audio = detect_nonsilent(response_audio, min_silence_len=50)[0]
            response_audio = response_audio[non_silent_audio[0]:non_silent_audio[1]]

            stream.write(response_audio.raw_data)
        else:
            print("Unexpected response format:", response)

    except Exception as e:
        print("Error:", e)

# stop audio stream
stream.stop_stream()
stream.close()
p.terminate()

Error:
error: Python 3.11.2 (v3.11.2:878ead1ac1, Feb  7 2023, 10:02:41) [Clang 13.0.0 (clang-1300.0.29.30)] on darwin
Type "help", "copyright", "credits" or "license()" for more information.

========= RESTART: /Users/alfiehoward-delamare/Documents/ai hog inc.py =========

Warning (from warnings module):
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pydub/utils.py", line 170
    warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)
RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work
Traceback (most recent call last):
  File "/Users/alfiehoward-delamare/Documents/ai hog inc.py", line 8, in <module>
    from pydub.utils import which, mediainfo, make_chunks, silence
ImportError: cannot import name 'silence' from 'pydub.utils' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pydub/utils.py)

========= RESTART: /Users/alfiehoward-delamare/Documents/ai hog inc.py =========

Warning (from warnings module):
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pydub/utils.py", line 170
    warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)
RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work
Traceback (most recent call last):
  File "/Users/alfiehoward-delamare/Documents/ai hog inc.py", line 8, in <module>
    from pydub.utils import which, mediainfo, make_chunks, silence
ImportError: cannot import name 'silence' from 'pydub.utils' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/pydub/utils.py)




  ai hog inc.py (Size: 2.49 KB / Downloads: 92)

Larz60+ write Mar-27-2023, 07:59 PM:
Please post all code, output and errors (it it's entirety) between their respective tags. Refer to BBCode help topic on how to post. Use the "Preview Post" button to make sure the code is presented as you expect before hitting the "Post Reply/Thread" button.

[jefsummers]

When posting code please use the Python tags in the toolbar. Otherwise you lose all indentation and your code becomes difficult to interpret.

The errors at the bottom suggest some libraries are not available in the current environment

[codiac]

When posting code please use the Python tags in the toolbar. Otherwise you lose all indentation and your code becomes difficult to interpret.

The errors at the bottom suggest some libraries are not available in the current environment

how do i get those libraries?

[deanhystad]

Looks like the problems are with pydub.

https://pypi.org/project/pydub/

Output:
Project description
Manipulate audio with an simple and easy high level interface.

See the README file for details, usage info, and a list of gotchas.

Did you read the README file?

Applicable information on this page:

https://github.com/jiaaro/pydub/

Installation
Installing pydub is easy, but don't forget to install ffmpeg/avlib (the next section in this doc)

...

Dependencies
You can open and save WAV files with pure python. For opening and saving non-wav files – like mp3 – you'll need ffmpeg or libav.