Project Info

StorySpark

This project did not submit a demo video on Devpost.

Inspiration

We were inspired by the power of storytelling in children's development. We wanted to create an interactive platform that fuels kids' imaginations, allowing them to craft their own stories through simple voice or text inputs, bringing their creativity to life with visuals and narration.

What it does

StorySpark is a kid-friendly platform that generates personalized stories from voice or text prompts, creates matching visuals, and narrates the story with a slideshow. It’s designed to be engaging and educational, sparking creativity while being easy to use. We also offer a terminal-friendly version for flexibility.

How we built it

We used the Gemini API for generating stories, LMNT for converting text to speech, and Deepgram for speech-to-text functionality. The Fetch.ai uAgents framework enables the terminal-friendly version, ensuring accessibility for all users. The core technologies work seamlessly to deliver a fun, interactive experience.

Challenges we ran into

One challenge was ensuring the seamless integration of the various APIs, especially managing real-time story generation, image creation, and audio synchronization. We also worked on optimizing the terminal version for users who prefer a non-browser experience.

Accomplishments we're proud of

We’re proud of building an engaging platform that brings together story generation, visuals, and audio for a unique storytelling experience. Successfully implementing the terminal version using Fetch.ai uAgents was another achievement that makes our platform versatile.

What we learned

We learned how to integrate multiple APIs effectively, ensuring smooth real-time interaction between story, visuals, and audio. Additionally, working with Fetch.ai uAgents gave us deeper insights into creating user-friendly terminal applications.

What's next

Next, we plan to enhance the AI capabilities to allow for more complex storylines, add more customization options for visuals, and introduce multilingual support. We’ll also continue refining the user experience and expanding the platform’s reach to engage more children globally.

Analysis

Compare with all teams

View

Metric

No commits on this project resolved to a GitHub account.

Technology

Found in codeClaimed only

CSSIn code
HTMLIn code
JavaScriptIn code
PythonIn code
ReactIn code
Google GeminiClaimed

5 of 6 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

29 KB

Source files

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

Feature verification

4 Verified2 Code-supported2 Claimed only

React frontend UIVerified
Built with, react
Claimed on Devposthigh confidence
- Frontend/package.json — react and react-dom are listed as dependencies and Frontend/src/App.js is a React functional component using hooks
Story generation from text prompt (Gemini)Verified
Generates personalized stories from text prompts using the Gemini API
Claimed on Devposthigh confidence
- Server/gemini_agent.py:52 — FastAPI '/gemini' endpoint calls chat.send_message on a genai GenerativeModel and returns the response text
- Frontend/src/App.js:130 — submitRequest() posts inputText to BASE_API + '/gemini' and stores the returned story text
Text-to-speech narration (LMNT)Verified
Narrates the story using LMNT text-to-speech
Claimed on Devposthigh confidence
- Server/lmnt_agent.py:33 — handle_text_to_speech() uses lmnt.api.Speech.synthesize() per sentence and returns base64-encoded wav audio
- Frontend/src/App.js:132 — submitRequest() posts story text to /lmnt, then decodeBase64Audio() builds a playable audio blob URL
Voice prompt input via speech-to-text (Deepgram)Verified
Users can create stories from voice prompts using Deepgram speech-to-text
Claimed on Devposthigh confidence
- Frontend/src/App.js:61 — handleRecord() records mic audio via MediaRecorder and sendAudioToAPI() posts base64 audio to /deepgram
- Server/deepgram_agent.py:111 — speech_to_text() decodes the blob to wav and calls Deepgram's transcribe_file, returning the transcript
Kid-friendly content filteringCode-supported
Kid-friendly platform designed to be engaging and educational for children
Claimed on Devpostmedium confidence
- Server/gemini_agent.py:31 — An inappropriate_words list and filter_inappropriate() function exist to flag unsafe words, but filter_inappropriate() is never called anywhere in the /gemini endpoint, so filtering is not actually wired into the response flow
Slideshow visuals accompanying the storyCode-supported
Narrates the story with a slideshow of matching visuals
Claimed on Devpostmedium confidence
- Frontend/src/App.js:21 — A slideshow UI cycles through images on a 5s interval and displays story text alongside, but the images array is a hardcoded list of 3 static files ('/images/7.png' etc.), not images generated to match the story
AI-generated matching visuals/images for the storyClaimed only
Creates matching visuals for the generated story
Claimed on Devposthigh confidence
Terminal-friendly version via Fetch.ai uAgentsClaimed only
Offers a terminal-friendly version built with the Fetch.ai uAgents framework
Claimed on Devposthigh confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.