StoryBuddy

Inspiration

Parents and educators struggle to create fresh, engaging stories. We wanted to make personalized storytelling effortless and magical.

What it does

StoryBuddy turns any photo into a unique story narrated in your own voice. Snap a picture, record 10 seconds of audio, and get an AI-generated tale with cloned voice narration.

How we built it

• Chrome's Prompt API (Gemini Nano) for on-device story generation
• External TTS service for voice cloning
• React with CSS for the interface

Challenges we ran into

Integrating Chrome's experimental Prompt API, handling audio recording, and coordinating streaming text generation with async TTS processing.

Accomplishments that we're proud of

Creating a fully functional pipeline from photo → AI story → personalized narration, all with a smooth user experience and real-time streaming.

What we learned

Working with cutting-edge browser AI APIs, audio processing in the browser, and building privacy-focused applications that run on-device.

What's next for StoryBuddy

More language support, story export features, a generated story history list and voice selection feature.

Built With

• css
• html
• indextts2
• javascript
• promptapi