How to Make Story Video for YouTube | How to Make Story Video | AI & ChatGPT

FitBot AI
14 Jun 202309:42

TLDRThis tutorial video teaches you how to create story videos for YouTube using AI and ChatGPT. It covers five key steps: crafting a compelling story, converting text to speech with tools like Naraka and 11 Labs, generating images and videos with Leonardo AI and creating parallax effects with Leapex, selecting background music from AIVA, and finally editing the video with CapCut. The example provided is a story about the Egyptian Pharaoh Firon, demonstrating how to use prompts to generate images and create a video that captivates the audience.


  • 📝 Create a compelling story: Use AI tools like Chat GPT to craft a narrative, ensuring you instruct it to 'create story' for a custom tale.
  • 🗣️ Generate voiceover: Utilize text-to-speech software, such as Naraka or 11 Labs, to convert your script into an audio format.
  • 🖼️ Produce images and videos: Employ AI image generation tools like Leonardo AI to create visuals that correspond with your story prompts.
  • 🌟 Add a parallax effect: Use platforms like Leapex to give your images a dynamic, video-like movement to enhance viewer engagement.
  • 🎵 Select background music: Access AI music platforms like AIVA to obtain background tracks that complement the mood of your story video.
  • ✂️ Edit your video: Compile all elements, including images, voiceover, and music, using video editing software like CapCut to finalize your video.
  • 🔍 Seek help with prompts: If not adept at writing prompts for images, ask Chat GPT for assistance to ensure they align with your story.
  • 🎭 Customize voiceover options: Choose from a variety of voices and languages on platforms like Google Text-to-Speech to match your video's style.
  • 🎨 Select multiple images: Generate multiple images per prompt to have options and ensure you select the ones that best fit your narrative.
  • 🔗 Combine visuals and audio: Sync your voiceover with the images and parallax effects to create a cohesive and engaging video experience.
  • 💻 Use various AI tools: The process involves leveraging different AI tools for story writing, image generation, voiceover creation, music selection, and video editing.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is how to make story videos for YouTube using AI and ChatGPT.

  • How many steps are involved in creating a story video as mentioned in the video?

    -There are five steps involved: story writing, text to speech, image and video generation, background music, and video editing.

  • What is the first step in creating a story video according to the video?

    -The first step is story writing, where you either use your own story or create one with the help of ChatGPT.

  • How can ChatGPT assist in creating prompts for generating images and pictures for the story?

    -ChatGPT can be instructed to 'create prompts for the story to generate images and pictures', which will help in visualizing the story.

  • What software is suggested for creating the voiceover for the video?

    -Two software options are mentioned: Naraka and 11 Labs, which can be used to convert text into voiceover.

  • What is the process of creating images for the story using Leonardo AI?

    -The process involves copying the prompts created by ChatGPT, pasting them into Leonardo AI, and generating images based on those prompts.

  • How can a parallax effect be created to enhance the video?

    -A parallax effect can be created using Leapex, where images are selected and processed to create a moving effect similar to a video style.

  • What platform is recommended for adding background music to the video?

    -AIVA is recommended for adding background music, where you can create tracks and download them for use in the video.

  • What video editing software is used in the video to finalize the story video?

    -CapCut is the video editing software used to import, arrange, and edit all the elements of the video to create the final product.

  • Can you provide an example of a title generated by ChatGPT for the story of Pharaoh Firon?

    -An example title generated by ChatGPT for the story of Pharaoh Firon is 'The Arrogance of Firon: A Tale of Power and Redemption in Ancient Egypt'.

  • How does the video guide the user in selecting the right voice for the text-to-speech software?

    -The video suggests using Google's text-to-speech voices, where users can choose from a variety of types like American English, British English, or other languages based on their preference.



📚 Introduction to Creating Story Videos with AI

The script introduces a tutorial on crafting story-based videos for YouTube using artificial intelligence and chatbots like GPT. The process is broken down into five key steps: story writing, text-to-speech conversion, image and video generation, background music selection, and video editing. The example used is a story about a powerful Egyptian Pharaoh named Firon. The video demonstrates how to use AI to generate a story, create prompts for image generation, and suggests tools for text-to-speech conversion, such as Narakeet and 11 Labs.


🎨 Image and Video Generation for Storytelling

This paragraph delves into the image and video generation phase of the video creation process. It details the use of Leonardo AI for generating images based on prompts derived from the story. The script provides a step-by-step guide on how to use the tool to create and download images, and then how to apply a parallax effect to these images using Leapex, turning them into moving visuals akin to video clips. The aim is to bring the static images to life, enhancing the storytelling aspect of the video.



💡Story Video

A 'Story Video' is a type of video content that tells a narrative, often with a beginning, middle, and end. It is designed to engage viewers by presenting a story that can be informative, entertaining, or inspirational. In the context of the video script, the main theme revolves around creating a story video for YouTube, using AI and ChatGPT to generate content, voiceover, images, and editing.


AI, short for Artificial Intelligence, refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. In the script, AI is utilized for creating the story content, generating images, and assisting in the overall video production process.


ChatGPT is a specific AI chatbot program designed to generate human-like text based on the prompts given to it. In the video script, ChatGPT is mentioned as a tool for creating the story of Pharaoh Firon in Egypt, generating prompts for images, and writing the story's title.

💡Story Writing

Story Writing is the process of crafting a narrative with characters, settings, and events. It is the first step highlighted in the script for making a story video. The script mentions using ChatGPT to assist in writing the story of an ancient Egyptian Pharaoh named Firon.


Text-to-Speech (TTS) is a technology that converts written text into audible speech. In the script, TTS is used to create a voiceover for the story video, with tools like Naraka and 11 Labs mentioned for this purpose.

💡Image and Video Generation

Image and Video Generation refers to the process of creating visual content either manually or using software. The script describes using AI tools like Leonardo AI for generating images based on story prompts and creating a parallax effect with Leapex to give a dynamic video feel.

💡Background Music

Background Music is the audio track that plays behind the main content of a video, enhancing the mood and atmosphere. The script mentions using a service like AIVA to create a custom music track for the story video.

💡Video Editing

Video Editing is the process of assembling and modifying video shots to create a finished video product. The script describes using a tool like CapCut to import images, voiceover, and music, and to edit them together into a cohesive story video.

💡Parallax Effect

The Parallax Effect is a visual phenomenon where nearby objects appear to move faster than those further away when observed from a moving vantage point. In the script, it is used to describe a technique in video creation where images move at different speeds to create a sense of depth.


Voiceover is a method of using narration to explain part of a story or to add information to visual content. In the context of the video script, voiceover is created using TTS software to read the story's text and provide audio for the video.


Prompts are stimuli or cues that elicit a response, in this case, used to guide AI in generating specific content. The script mentions creating prompts for ChatGPT to generate images and pictures that align with the story of Pharaoh Firon.


Introduction to creating story videos for YouTube using AI and ChatGPT.

The four essential steps to create story videos: story writing, text-to-speech, image and video generation, background music, and video editing.

Utilizing ChatGPT for story creation with a specific focus on the story of Pharaoh Firon in ancient Egypt.

The importance of clear instructions for ChatGPT to generate the desired story.

Creating prompts for image generation with the help of ChatGPT.

Generating a compelling title for the story using ChatGPT.

Using Narakit and Google Text-to-Speech for creating voiceovers.

Selecting the appropriate voice and creating audio segments for the video.

Alternative voiceover creation with 11 Labs and its ease of use.

Image generation using Leonardo AI and creating visuals for the story.

Creating a parallax effect with Leapex to enhance video storytelling.

The process of turning still images into dynamic video clips.

Selecting background music from AIVA to complement the video's narrative.

Finalizing the video with editing using software like CapCut.

Importing and arranging video clips, voiceovers, and music in the editing timeline.

Exporting the final video after editing and reviewing.

The complete workflow from story creation to video export using AI tools.