In videos, description and keywords play an important role in the choosing process of the right video to watch. The main idea of the proposed approach is to generate descriptions and timestamps for videos automatically. Our approach plays a role in reducing the time consumed searching for the proper video. Timestamps would help to find and watch only the desired part of the video. One of the main goals of our approach is keyword extraction. Firstly the video content appears in the frame and outputs a summarized text for the video content. Secondly, emotion and how it changes during a specific period. Thirdly, the audio transcribed into the text occurs and output an abstractive summarization of the audio. Finally, the fusion happens between all summarizations using natural language processing techniques. Techniques as tokenization, sentence segmentation, and lemmatization, stemming, and then abstractive summarization. Video summarization occurs to get a meaningful description of the video.

• To describe the videos with high accuracy based on video frames and audio.

• Fusion between summary of frames and audio with emotions to get the best description.

• To timestamp the video (displaying the start time of different topics within one video) for easy navigation.

1. Help video content creators by creating description and time-stamps for video.

2. Describe the video based on frames.

3. Describe the video based on speech.

4. Apply text Fusion between these two description alongside with the dominant emotion to output one meaningful description for the video.

5. Timestamps will also be based on speech or frames according to video type.System Scope Text