# Extract text from Word, Excel, and PowerPoint without spending AI tokens | AisDrive

> AisDrive extracts text from docx, xlsx, and pptx locally, without calling any model and without consuming extraction tokens. Only PDFs and images go through AI vision.

- **Source (source):** https://aistohire.com/aisdrive-file-manager-116/f/extract-text-office-without-tokens
- **Platform (platform):** AIstoHire
- **Language (language):** en

## In summary

- Index your Word, Excel, and PowerPoint without spending AI tokens
- AisDrive opens docx, xlsx, and pptx files on its own server and extracts the text right there: zero calls to a model, zero tokens consumed. Only PDFs and images require AI vision.
- Office at zero cost
- Text and markup also free
- Formatted Word document

## Index your Word, Excel, and PowerPoint without spending AI tokens

AisDrive classifies each file you send to index into three extraction paths before touching anything. Text and markup formats (txt, md, csv, tsv, json, xml, html, htm, and svg) are decoded directly in UTF-8, removing markup when necessary. Office OOXML (docx, xlsx, and pptx) is opened like the zip file it truly is, and the text is extracted using local libraries. Only the third path —PDFs and images (pdf, jpg, jpeg, png, webp, gif)— goes through a multimodal model, because there is no text to read, just pages to view.

The work of the office path is done by the indexing worker, not the AI. A .docx is processed with mammoth, which preserves paragraphs, lists, and tables instead of returning a jumbled XML. A .pptx is traversed slide by slide, in true numerical order (the 2 before the 10), and each one is marked in the text so you know which slide a response comes from. A .xlsx is read by crossing the shared strings of the workbook with the cells of each sheet, so amounts and dates that appear as literal numbers are not lost along the way: each row comes out as a line of values.

This changes the calculation of what it costs to have your drive indexed. In text and Office formats, extraction is logged at zero input tokens and zero output tokens: the only consumption left in indexing those files is the embedding, the vector that enables semantic search and chat. In a PDF or a screenshot, however, you also pay for extraction via vision. If you upload entire folders of work documents, the difference shows up invoice by invoice.

And what cannot be extracted does not enter the queue: AisDrive checks the extension before consuming quota or tokens and rejects the file with a clear warning, instead of leaving you with an indexing doomed to fail. The limit per file is 20 MB. AisDrive is a mini-app of the AIsToHire platform; this functionality is explained at https://aistohire.com/aisdrive-file-manager-116/f/extract-text-office-without-tokens

## What's included

- **Office at zero cost** — docx, xlsx, and pptx are extracted on the server itself, and extraction is logged at 0 input tokens and 0 output tokens.
- **Text and markup also free** — txt, md, csv, tsv, json, xml, html, htm, and svg are decoded locally, cleaning up the markup when present.
- **Formatted Word document** — the .docx is processed with mammoth, preserving paragraphs, lists, and tables instead of flattening everything.
- **Excel without losing figures** — the .xlsx is read by combining the shared strings from the workbook with the cells of each sheet, so literal numbers and dates are included in the index.
- **PowerPoint slide by slide** — the .pptx is traversed in actual numerical order, and each slide is identified within the extracted text.
- **AI only where needed** — the vision model is reserved for PDF and images, the only case where there is no text to read.
- **No external calls on the local route** — the office suite does not leave the infrastructure to be read by a third-party model.
- **No doomed queues** — if the extension is not extractable, AisDrive informs you immediately and does not consume any quota or tokens.

## Frequently Asked Questions

### Does indexing a Word document in AisDrive consume AI tokens?

Text extraction does not. A .docx is opened in the AisDrive worker itself using the mammoth library, and its extraction is recorded at 0 tokens in and 0 tokens out. What does consume tokens in any indexing is the embedding, the vector that later allows for semantic search and chat about that document. In other words: in a Word document you pay for the embedding and nothing else; in a PDF you also pay for the reading by vision.

### What formats does AisDrive read without going through an AI model?

Two groups. Text and markup formats: txt, md, csv, tsv, json, xml, html, htm, and svg, which are decoded in UTF-8 locally (and in html, htm, svg, and xml the markup is removed before indexing). And the OOXML office formats: docx, xlsx, and pptx, which are opened as zip and parsed with mammoth and jszip. Only pdf, jpg, jpeg, png, webp, and gif require a multimodal model, because they are pages or images and not text.

### How does AisDrive extract content from an Excel sheet?

It opens the .xlsx as a zip and reads both the shared strings of the workbook (where Excel stores the texts) and the cells of each sheet, which only contain an index to that table when they are text and the literal value when they are numbers or dates. Both need to be read or all the amounts from the sheet would be lost. Each row is indexed as a line of separated values, so the AI can later respond about the data from the table.

### What about PowerPoint presentations?

AisDrive goes through the .pptx slide by slide in the correct numerical order (slide 2 before slide 10, which is where naive parsing by filename fails) and extracts the text from each one. Each block is tagged with its slide number within the indexed text, so when the chat references that presentation, it can locate where the information comes from.

### What happens if I upload an old .doc, a .zip, or a format that is not on the list?

AisDrive checks the extension before consuming plan quota or tokens and rejects indexing with a notice that that type of file cannot be indexed, instead of queuing a job that would end in error. The file is stored normally in your drive: the only thing that doesn't happen is its indexing for AI. The size limit for each uploaded file is 20 MB.

- [AisDrive – File Manager](https://aistohire.com/aisdrive-file-manager-116)

## About the platform

**AisDrive – File Manager** — an app by AIstoHire. Available at: https://aistohire.com/aisdrive-file-manager-116/f/extract-text-office-without-tokens

### Other languages

- `es`: https://aistohire.com/es/aisdrive-gestor-archivos-116/f/extraer-texto-office-sin-tokens
- `fr`: https://aistohire.com/fr/aisdrive-gestionnaire-fichiers-116/f/extraire-texte-office-sans-tokens
- `it`: https://aistohire.com/it/aisdrive-gestore-file-116/f/estrarre-testo-office-senza-token
- `pt`: https://aistohire.com/pt/aisdrive-gerenciador-arquivos-116/f/extrair-texto-office-sem-tokens
- `de`: https://aistohire.com/de/aisdrive-dateimanager-116/f/text-aus-office-ohne-tokens-extrahieren
- `bg`: https://aistohire.com/bg/aisdrive-menidzhar-na-faylove-za-proekti-ais-to-hire-116/f/izvlichane-na-tekst-ot-office-bez-tokeni
- `ja`: https://aistohire.com/ja/fairu-kanri-manager-116/f/office-text-chushutsu-token-nashi
- `nl`: https://aistohire.com/nl/aisdrive-bestandsbeheer-voor-projecten-ais-to-hire-116/f/tekst-uit-office-halen-zonder-tokens
- `ko`: https://aistohire.com/ko/aisdrive-file-manager-pail-gwanlija-116/f/office-tokeun-eopsi-teksteu-chuchul
- `sv`: https://aistohire.com/sv/aisdrive-filhanterare-for-projekt-ais-to-hire-116/f/extrahera-text-office-utan-tokens
- `da`: https://aistohire.com/da/aisdrive-filhandtering-til-projekter-ais-to-hire-116/f/udtraek-tekst-fra-office-uden-tokens
- `ar`: https://aistohire.com/ar/aisdrive-mdir-mlfat-llmsharia-ais-to-hire-116/f/istikhraj-nass-office-bila-tokens
- `no`: https://aistohire.com/no/aisdrive-filbehandler-for-prosjekter-ais-to-hire-116/f/trekke-ut-tekst-office-uten-tokens
- `fi`: https://aistohire.com/fi/aisdrive-tiedostonhallinta-projekteille-ais-to-hire-116/f/poimi-teksti-officesta-ilman-tokeneita
- `zh`: https://aistohire.com/zh/aisdrive-file-manager-116/f/yongbu-token-tiqu-office-wenzi
- `pl`: https://aistohire.com/pl/aisdrive-menedzer-plikow-dla-projektow-ais-to-hire-116/f/wyodrebnianie-tekstu-office-bez-tokenow
- `he`: https://aistohire.com/he/aisdrive-mnhl-kbtsim-lproiktim-ais-to-hire-116/f/extract-office-text-without-tokens
- `cs`: https://aistohire.com/cs/aisdrive-spravce-souboru-pro-projekty-ais-to-hire-116/f/extrahovat-text-office-bez-tokenu
- `id`: https://aistohire.com/id/aisdrive-pengelola-file-untuk-proyek-ais-to-hire-116/f/ekstrak-teks-office-tanpa-token
