audios = []
        inputs = []
        #generate an empty audio
        e_aud_src = rendering_helper.generate_empty_audio(0.1)
        e_aud = (
            ffmpeg.input(e_aud_src)
                .audio
        )

        for k, i in enumerate(videos):
            inp = ffmpeg.input(i['src'], ss=i['start'],  t=(i['end'] - i['start']))

            inp_f = (inp.filter_multi_output('split')[k]
                        .filter_('scale', width=(i['width'] * Factors().factors['w_factor']), height=(i['height'] * Factors().factors['h_factor'])).filter('setsar', '1/1')
                        .setpts(f"PTS-STARTPTS+{i['showtime']}/TB"))

            audio = ffmpeg.probe(i['src'], select_streams='a')
            if audio['streams'] and i['muted'] == False:
                a = (inp.audio.filter('adelay', f"{i['showtime'] * 1000}|{i['showtime'] * 1000}"))
            else: 
                a = e_aud
            audios.append(a) 

            e_frame = (e_frame.overlay(inp_f, x=(i['xpos'] * Factors().factors['w_factor']), y=(i['ypos'] * Factors().factors['h_factor']), eof_action='pass'))

        
        mix_audios = ffmpeg.filter_(audios, 'amix') if len(audios) > 1 else audios[0]
        inp_con = ffmpeg.concat(e_frame, mix_audios, v=1, a=1)
        return inp_con