Pixtale

What it does

Pixtale is an AI-powered app that transforms your trip photos and videos into narrated video stories. Here's how it works:
1. Upload: Users upload a zip file with trip media or select a Google Photos album.
2. Metadata Extraction: The app extracts date, time, and GPS data from the media.
3. AI Description Generation: This is where Gemini API shines:
- Gemini Flash generates descriptions for individual photos and videos.
- Gemini 1.5 Pro takes these descriptions as input and crafts a cohesive narrative script, scene by scene.
4. Audio Narration: Google's Text-to-Speech API converts the script into audio.
5. Video Creation: FFmpeg combines the narration with the original media to create the final video.
6. Social Media Content: Pixtale goes further by generating:
- Captions and hashtags for sharing
- A mini blog post summarizing the trip (also using Gemini 1.5 Pro)
7. User Customization: Users can edit location details for each scene using the Google Maps API.
Pixtale leverages Gemini's ability to interpret visual data, understand context, generate coherent and engaging content and craft narratives that feel personal and authentic. This AI-driven approach allows for the rapid creation of rich, multimedia travel stories that would be time-consuming to produce manually.