Inspiration
The purpose of StoryGem Studio is to stimulate ideas and act of creativity for anyone to be able to create and share their creations with others, experiment in an online studio environment and express themselves through this medium.
A digital storytelling AI tool for content creators can prove to be a powerful tool for education, media, entertainment, marketing and brand engagement.
AI Generative content tools can decrease disparities in digital access and literacy, broaden access while helping to level the playing field and ultimately bridging the digital divide. Reducing the digital divide in this way could lead to improved outcomes in the society, foster creativity, and innovation.
Research shows that global video content consumption is predicted to grow by a whopping 82% in 2025, while video streaming will make up 91% of global internet traffic. The need for scalable and efficient video creation tools is greater than ever. Video content is king.
What it does
It provides automation in storytelling, image and video production.
Boosts Content Output: Reduces the time needed to create images, videos, enabling creators to publish more frequently.
Automated Image and Video Creation: It combines images, audio, and text to produce ready-to-use or experimental videos for realtime AI-powered interactive transmedia storytelling which can also be distributed on social media platforms.
How we built it
AO and BetterIDEa IDE: The Lua based process or smart contract is used to store the image URL after generated using OpenAI. The process is used to retrieve all the images on AO.
OpenAI: It is used to generate images based on input prompts.
Gemini API: It is used to generate video scripts with multiple prompts for generating multiple images. It also provides multiple prompts for generating an audio file content in MP3 format.
Replicate: It is used for generating images based on text prompts.
Assembly AI: It is used for adding the video captions.
Google Cloud Text-to-Speech: Translate text (script) to speech (the MP3 audio file). A text-to-speech service converts the content text into natural-sounding speech, which is delivered to the user in the video.
Remotion: It is used for generating the videos and bringing it all together.
What's next for StoryGem AI Studio
Integration of AI agent with AO, Arweave, and ArFleet 2D and 3D generation of AI Avatars Adding more features for content creation, such as scriptwriting, editing, or animation. Enhanced Image, Video, Avatar, and Story studios Digital right and ownership of content. Make it easy to adjust content element.
Log in or sign up for Devpost to join the conversation.