Sales invoice extraction for Indian sellers

Your own sales invoices are the documents you generate, which makes them feel like the easy ones, but outward invoices still have to be turned into rows for your books, for Tally data, and, when preparing GSTR-1, for your return data. Each sale is an invoice with line items, HSN/SAC codes, a taxable value, and a tax split that has to be right by customer and by place of supply. Dynamite Docs extracts your own sales invoices, credit notes, and debit notes, pulling GSTIN, line items, HSN/SAC, taxable value, the CGST/SGST/IGST split, and totals into confidence-scored rows you review and export for Tally or Excel.

Try this workflow free or view pricing.

Your outward invoices still become keystrokes

Outward invoices come from your own billing software, so the layouts are consistent, but the volume of line items grows with every sale, and the rows still have to be built by hand or by fragile spreadsheet exports.
Sales are not only invoices. Credit notes for returns and debit notes for corrections are outward documents too, and each has to be captured so the outward picture stays complete.
The tax split on your own sales has to be right by place of supply: CGST and SGST for intra-state sales, IGST for inter-state sales. A mis-assigned state is exactly the kind of error that shows up later as a mismatch.
Line-item HSN/SAC detail is where most exports fall apart. PDF exports flatten or drop the per-line codes, so preparing data for GSTR-1 means rebuilding the line structure by hand.

How Dynamite Docs handles your outward invoices

01 — Drop the outward batch in

Upload your own sales invoices, credit notes, and debit notes as PDFs, scans, or photos. Clean digital exports from your billing software are parsed deterministically from their text layer: no AI call, identical results every time.

02 — Schema inferred, not built

Your GSTIN, customer GSTIN, invoice number and date, line items, HSN/SAC, taxable value, CGST, SGST, IGST, and totals are read from each layout on the spot. There is no template library to maintain for your own formats.

03 — Review by confidence, not retyping

Every field carries a confidence score. You check the handful of low-confidence values, usually a line total, an HSN/SAC on a handwritten sales bill, or a tax split that doesn’t tie to the taxable value, and each correction becomes a pattern the next batch reuses.

04 — Export and prepare

Export to Excel, CSV, or JSON, or push rows to Google Sheets. When preparing GSTR-1, hand the structured rows to your team or your CA; the return itself and filing stay outside Dynamite Docs, and current rules should be checked on the GST portal and with your tax advisor.

Document types this workflow handles

Sales invoice PDFs — digital outward invoices parsed deterministically
Sales invoice photos — photographed invoices and handwritten sales bills
Credit notes — reductions to earlier sales
Debit notes — increases or corrections to earlier sales

What gets extracted from a sales invoice

The exact fields are inferred per layout. A typical sales invoice run yields these, each confidence-scored:

Your GSTIN — 27AAACD1234F1Z5
Customer GSTIN — 29AABCC3456C1ZD
Invoice number — SI-2026-0881
Invoice date — 2026-08-11
HSN / SAC code — 8467
Item & quantity — Rotary hammer × 6
Taxable value — ₹1,86,000.00
CGST / SGST amount — ₹0.00
IGST amount — ₹33,480.00
Invoice total (incl. tax) — ₹2,19,480.00

A realistic example

Your outward invoices, credit notes, and debit notes extract to rows like these, ready to review and export when preparing GSTR-1 or for entry into Tally:

Document #	Type	Date	Customer	Customer GSTIN	HSN/SAC	Item	Qty	Taxable value	CGST	SGST	IGST	Total
SI-2026-0881	Invoice	2026-08-11	Meenakshi Hardware	29AABCC3456C1ZD	8467	Rotary hammer	6	₹1,86,000	—	—	₹33,480	₹2,19,480
SI-2026-0882	Invoice	2026-08-12	Sri Venkateswara Traders	36AABCV2871Q1ZB	4820	A4 copier paper	25	₹15,000	₹1,350	₹1,350	—	₹17,700
CN-2026-011	Credit note	2026-08-14	Meenakshi Hardware	29AABCC3456C1ZD	8467	Returned rotary hammer	-1	-₹31,000	—	—	-₹5,580	-₹36,580

The seller side of your own documents

The seller side is a mirror of the buyer side, with one difference: the invoices are yours. The formats come from your own billing software, so they are consistent, but the data still has to leave the PDF and become rows, line by line. The GSTIN, the HSN/SAC codes, the taxable value, and the tax split all have to survive that move intact, because they are the same fields your buyers are extracting from the very same invoice.

Credit notes and debit notes are outward documents too. Returns, rate corrections, and billing adjustments all move the outward picture, and a month is only complete when the notes are captured alongside the invoices. The same extraction treats a credit note as just another table, and its rows line up against the original sale.

The inter-state and intra-state split is the field most worth checking. CGST and SGST apply to intra-state sales and IGST to inter-state sales, so the place of supply on each invoice decides which split appears in the rows. Confidence-scored extraction keeps the split visible for review instead of burying it in a retyped total.

Preparing GSTR-1 is your team’s job, and the rows make it easier, not automatic. Dynamite Docs is a document-processing and data-preparation layer: it extracts your outward invoices and hands you clean rows. When preparing GSTR-1, consult the GST portal and your tax advisor for current rules. Filing, decisions, and review stay with you and your CA.

Why bring-your-own-AI matters for sales invoice extraction

Your outward invoices are consistent because they come from your billing software, but the line-item HSN/SAC detail and the CGST/SGST versus IGST split by place of supply still have to survive the move from PDF to rows. The reader that does that surviving is your choice, at your provider’s rate with zero markup, unlimited on Pro and Ultra.

Your own billing-software exports parse deterministically for free, identical results every run. Photographed sales bills and handwritten notes are read by the vision model you pick, so you control quality and per-page cost on exactly the documents that need it.

The outward rows, invoices, credit notes, and debit notes together, are the input your CA works from when preparing GSTR-1. Corrections your team makes are remembered per layout, and the exported rows stay yours for Tally, Excel, or your own books.

Questions, answered

Can it read sales invoices from our own billing software?

Digital exports from your billing software carry an embedded text layer, so they are parsed deterministically, no AI call, identical results every time. Photographed or handwritten sales bills are read by the vision model you choose, with the same schema inferred.

Does it capture credit and debit notes as well as invoices?

Yes. Credit notes and debit notes are treated as document types of their own, so reductions and corrections are captured alongside the sales invoices and line up against the original sales.

Does it split CGST+SGST from IGST on outward invoices?

Yes. Taxable value, CGST, SGST/UTGST, IGST, and the invoice total come out as separate confidence-scored fields, so the intra-state and inter-state split can be checked against the total before anything reaches your books.

Does Dynamite Docs prepare or file GSTR-1?

No. Dynamite Docs extracts and structures your outward invoices into confidence-scored rows you export. When preparing GSTR-1, consult the GST portal and your tax advisor for current rules; preparing the return and filing remain with your team and your CA.