app.py

import numpy as np
import requests
import os
from scipy.io.wavfile import write

def main_function(audio):
    os.makedirs("out", exist_ok=True)
    write('test.wav', audio[0], audio[1])
    data = {
        'api_token': '171afdabea68ffcdbd7f102b8611ac63',
        'return': 'apple_music,spotify',
    }
    files = {
        'file': open('test.wav', 'rb'),
    }
    result = requests.post('https://api.audd.io/', data=data, files=files)
    artist = result.json()['result']['artist']
    title = result.json()['result']['title']
    genre = result.json()['result']['apple_music']['genreNames']
    image_url = result.json()['result']['spotify']['album']['images'][0]['url']
    return artist, title, genre, image_url

with gr.Blocks() as demo:
  with gr.Row():
    audio_input = gr.Audio(
        sources=["upload", "microphone"],
        waveform_options=gr.WaveformOptions(
            waveform_color="#01C6FF",
            waveform_progress_color="#0066B4",
            skip_length=2,
            show_controls=False,
        ),
    )
  with gr.Row():
    artist_output = gr.Textbox(label="Artist", show_copy_button=True)
    title_output = gr.Textbox(label="Music", show_copy_button=True)
    genre_output = gr.Textbox(label="Genre", show_copy_button=True)
  with gr.Row():
    image_output = gr.Image(label="Cover")

demo.launch(inputs=audio_input, outputs=[artist_output, title_output, genre_output, image_output])