# Project export: Gesture AI

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: TreeHacks 2024
- Tagline: Introducing a novel way to engage: AI-powered personalized videos that forge deep connections, drive conversions and captivate audiences. Elevate your brand with the unmatched power of personalization
- Devpost: https://devpost.com/software/gesture-ai-42lkom
- GitHub: not linked
- Demo: https://www.canva.com/design/DAF9BXcghzI/jCMyVKrfc8XfLE70SU6djg/view?utm_content=DAF9BXcghzI&utm_campaign=designshare&utm_medium=link&utm_source=editor
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

Inspired by Tints clothing brand (www.tintsstreetwear.com), we saw how personalized video thank-yous and abandoned cart follow-ups significantly boosted conversion rates and lowered CAC. Building relationships before sales proved effective but was extremely time-consuming, requiring manual efforts like social media interactions, content reposting, and connecting over shared interests. We are on a mission to assist millions of small business owners in accelerating the growth of their companies through AI-powered technology that decreases cost, and saves time

### What it does

Gesture AI introduces an AI-Powered Video Personalization Tool that closes the gap in human element AI sales tools, improving business follow-ups and nurturing relationships through video automation, facial cloning, and synthetic media integration.

### How we built it

By harnessing advanced AI technologies, we developed a system that transforms text into speech for video automation and uses lip-sync technology for realistic personalization. From uploading a contact list to deploying personalized videos through a batch API on GCP, our process uses OpenAI for script customization, ElevenLabs for audio generation, and a fine-tuned model for video synthesis, all invoked from the front-end.

### Challenges we ran into

We faced challenges in creating ultra-realistic personalized videos and ensuring the seamless integration of synthetic media for genuine interactions.

### Accomplishments we're proud of

We are proud to have expanded our AI tool's capabilities across languages, enabling brands to personalize ads for customers in different languages, such as Spanish.

### What we learned

We learned about the crucial importance of personalization in the modern digital landscape and AI's potential to revolutionize traditional marketing strategies, fostering authentic customer connections.

### What's next

We plan to broaden our market reach in B2B e-commerce and further optimize our platform to make it realistic. Additionally, we plan on expanding our influence beyond the e-commerce space into areas such as advocacy where personalized outreach can create societal change.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- FastAPI (technology) — claimed on Devpost, not found in the code
- Next.js (technology) — claimed on Devpost, not found in the code
- OpenAI (technology) — claimed on Devpost, not found in the code
- React (technology) — claimed on Devpost, not found in the code
- Tailwind CSS (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.