app.py

# app.py
# =============
# This is a complete app.py file for a Gradio application that allows users to upload an audio file and generate a video with frequency visualization.

import gradio as gr
import numpy as np
import matplotlib.pyplot as plt
import librosa
import librosa.display
import cv2
import os
import moviepy.video.io.ImageSequenceClip

# Function to generate frequency visualization frames from audio
def generate_frequency_visualization(audio_path):
    # Load the audio file
    y, sr = librosa.load(audio_path)

    # Perform Short-Time Fourier Transform (STFT)
    D = librosa.amplitude_to_db(np.abs(librosa.stft(y)), ref=np.max)

    # Create a directory to save the frames
    os.makedirs('frames', exist_ok=True)

    # Generate and save each frame
    for i, frame in enumerate(D.T):
        plt.figure(figsize=(10, 6))
        librosa.display.specshow(frame.reshape(1, -1), sr=sr, x_axis='time', y_axis='log')
        plt.axis('off')
        plt.savefig(f'frames/frame_{i:04d}.png', bbox_inches='tight', pad_inches=0)
        plt.close()

    return 'frames'

# Function to create a video from the generated frames
def create_video_from_frames(frames_directory):
    # Get the list of frame files
    frame_files = [os.path.join(frames_directory, f) for f in os.listdir(frames_directory) if f.endswith('.png')]
    frame_files.sort()

    # Create a video from the frames
    clip = moviepy.video.io.ImageSequenceClip.ImageSequenceClip(frame_files, fps=30)
    video_path = 'output_video.mp4'
    clip.write_videofile(video_path, codec='libx264')

    return video_path

# Gradio interface function
def process_audio(audio):
    audio_path = audio
    frames_directory = generate_frequency_visualization(audio_path)
    video_path = create_video_from_frames(frames_directory)
    return video_path

# Create the Gradio interface
iface = gr.Interface(
    fn=process_audio,
    inputs=gr.Audio(source="upload", type="filepath"),
    outputs=gr.Video(label="Generated Video"),
    title="Audio Frequency Visualization",
    description="Upload an audio file to generate a video with frequency visualization."
)

# Launch the Gradio interface
if __name__ == "__main__":
    iface.launch()

# Dependencies
# =============
# The following dependencies are required to run this app:
# - librosa
# - numpy
# - matplotlib
# - opencv-python
# - moviepy
# - gradio
#
# You can install these dependencies using pip:
# pip install librosa numpy matplotlib opencv-python moviepy gradio