Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Udhaar Voice: a credit ledger you fill by talking, built for shopkeepers, running with no internet

Description and use

Udhaar Voice lets shopkeepers record credit sales by speaking, transcribing locally with Whisper, parsing with Gemma, storing in SQLite, and auto‑generating overdue reminders, all offline.

Problem

Shopkeepers often record credit sales in paper notebooks, leading to missed entries, messy handwriting, and unclear month‑end balances.

Outcome

Udhaar Voice enables shopkeepers to record credit sales by speaking, eliminating paper, reducing errors, and providing instant balance and reminder generation without internet.

Workflow

  • Record a short voice note in the shopkeeper’s native language.
  • Transcribe the audio locally with Whisper (faster‑whisper).
  • Parse the transcript with a local Gemma model via Ollama to extract customer, items, amount, due date, and type.
  • Confirm the parsed entry before saving.
  • Save the entry to a SQLite ledger and update the running balance.
  • Generate a one‑tap reminder message for overdue customers.

Evidence

Small neighbourhood shops (kirana stores, tailors, tiffin kitchens, repair stalls) sell on credit all the time. "Ravi anna took 2 kg rice and oil, he'll pay Saturday." That sentence goes into a paper notebook, if it gets written down at all.

Source

Udhaar Voice lets the shopkeeper say the entry in their own language, in a short voice note, and the system does the rest: Transcribes the audio using Whisper, running locally; Understands the sentence with a local Gemma model and pulls out: customer name, items, amount, and promised pay date; Updates a ledger (one SQLite file) and keeps each customer's running balance; Generates a reminder message for any customer overdue, ready to send in one tap

Source

Step 1: transcribe locally with faster-whisper.

Source

Step 2: turn the sentence into structured data with a local Gemma model.

Source

Step 3: save to the ledger and keep a running balance.

Source

  • Record date: 2026-10-13T10:41:08.874Z