Finalist
StoreUp
StoreUp — talk your shop onto ONDC.
Core trick
Streams camera frames and speech to Gemini Live, then emits a Beckn v1.2.0 catalog from confirmed product items.
Description
StoreUp — talk your shop onto ONDC.
Millions of small shopkeepers in India want to sell online but are locked out by a language barrier, complicated forms, typing, and having to photograph every product. StoreUp removes all of it: a shopkeeper simply talks in their own language and shows their shelf to the phone camera, and StoreUp builds and publishes their online store on India's ONDC network — in minutes, with zero typing.
It's built entirely around the Gemini Live API's real-time, multimodal loop: the agent sees the shelf and hears the shopkeeper continuously. It recognizes products by brand, counts what it sees, proactively points out items the shopkeeper didn't mention, checks fair market prices live via Google Search grounding, and switches instantly between Indian languages mid-conversation. On confirmation, it names the store and generates a valid ONDC Beckn v1.2.0 catalog, while Nano Banana 2 Lite auto-generates product images — so the storefront looks real with no photos taken. A mock ONDC buyer app shows the store live.
This is impossible as a typed chatbox — the value is entirely in the live see-and-hear interaction.
README excerpt
# StoreUp — Talk your shop onto ONDC
**Turn any local shop into a live online store just by walking through it and talking.**
A shopkeeper points their phone at the shelf and speaks in their own language.
StoreUp *sees* the products through the camera, *hears* the shopkeeper live,
confirms each item conversationally, and publishes a valid **ONDC** catalog that
buyers across India can shop — no typing, no forms, no English required.
> Built for the **Google DeepMind Bangalore Hackathon** — Problem Statement 1:
> *Real-Time Multimodal Interaction* (Gemini Live API), with **Nano Banana 2
> Lite** driving a real-time product-image pipeline.
---
## Why this isn't "a chatbox with a mic"
The whole experience is built around the live, multimodal loop — it would be
impossible to do typed into a text box:
- **Sees + hears continuously.** The camera feed and microphone stream to Gemini
Live at the same time. The assistant recognizes products by brand/variant as
they come into view ("Oh, those are Lay's Classic").
- **Interruptible + real-time.** You can talk over it, correct it mid-sentence,
and it adapts instantly.
- **Speaks any Indian language.** Hindi, Kannada, Tamil, Telugu, English or a
mix — and switches the moment the shopkeeper switches.
- **Proactive vision.** It points out products you *didn't* mention, and asks
("how many of those?") instead of guessing counts it can't see clearly.
---
## How it works (end to end)
```
Phone (React PWA) Fas