import gradio as gr
import io
import os
import subprocess
import time
from datetime import datetime

def video_to_audio_tab():
    def video_to_audio(video):
        base_output_path = os.path.join(os.getcwd(), 'output', 'video2audio')
        output_file_name = "{datetime}.wav".format(datetime=datetime.now().isoformat().replace(':', '-'))
        output = os.path.join(base_output_path, output_file_name)
        command = "ffmpeg -i {video} -map a {output}".format(video=video, output=output)
        subprocess.call(command,shell=True)
        return output

    with gr.Tab("video2audio"):
        with gr.Row():
            video_input = gr.Video()
            with gr.Column():
                audio_output = gr.Audio()
                video_to_audio_button = gr.Button(value="Extract", variant="primary")
                video_to_audio_button.click(video_to_audio, inputs=video_input, outputs=audio_output)
                with gr.Row():
                    text_button = gr.Button("Send to Extract voice")
                    text_button = gr.Button("Send to Extract instrumental")

def audio_to_video_tab():
    def audio_to_video(audio, image):
        base_output_path = os.path.join(os.getcwd(), 'output', 'audio2video')
        output_file_name = "{datetime}.mp4".format(datetime=datetime.now().isoformat().replace(':', '-'))
        output = os.path.join(base_output_path, output_file_name)

        command = "ffmpeg -loop 1 -i {image} -i {audio} -c:v libx264 -tune stillimage -c:a aac -b:a 192k -pix_fmt yuv420p -shortest {output}".format(image=image, audio=audio, output=output)
        subprocess.call(command,shell=True)
        return output

    with gr.Tab("audio2video"):
        with gr.Row():
            with gr.Column():
                audio_input = gr.Audio(label="Input audio", type="filepath")

                with gr.Blocks():
                    with gr.Tab("Image"):
                        image_input = gr.Image(label="Input image", type="filepath")
                    # gr.Tab("Video")

            with gr.Column():
                video_output = gr.Video(label="Output video")
                create_video_button = gr.Button(value="Merge audio with provided media", variant="primary")
                create_video_button.click(audio_to_video, inputs=[audio_input,image_input], outputs=video_output)

with gr.Blocks() as demo:
    video_to_audio_tab()
    audio_to_video_tab()
    # gr.Tab("Extract voice")
    # gr.Tab("Extract instrumental")
    # gr.Tab("Change voice")
    # gr.Tab("Merge audio")

demo.launch()