> For the complete documentation index, see [llms.txt](https://evidano.gitbook.io/ailyze-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://evidano.gitbook.io/ailyze-docs/getting-started/convert-your-first-image-to-text.md). # Convert Your First Image to Text Turn photographed or scanned pages into editable text with the Image to Text workflow, check a free sample first, then correct and export the result. This page shows you how to turn your first scanned or photographed pages into editable text with the **Image to Text** workflow, for anyone whose notes, questionnaires, or archive pages exist only as pictures. For the full walkthrough, see [Convert Images & PDFs to Text](/ailyze-docs/prepare-research-data/convert-images-and-pdfs-to-text.md); for what every button does, see [Image to Text Settings](/ailyze-docs/reference/settings/image-to-text.md). ## Before you start * An Evidano account. Your first pages are free; see [Plans, Limits & Credits](/ailyze-docs/reference/plans-limits-and-credits.md). * Pictures of pages (PNG, JPG, JPEG, WEBP, HEIC, HEIF, BMP, or TIFF) or a PDF. One project holds images or PDFs, not both. No pages to hand? Download the two invented sample field-note pages below. * Pages you can read yourself. A blurry photo gives blurry text. ## Step 1: Open Image to Text and add your pages From your account page, click **Image to Text**. The wizard has three steps: **Add files**, **Language & domain**, and **Review and create**. 1. Type a **Project name**, or leave it blank to use today's date. 2. Drag your pages onto the drop zone, click **Browse files**, or pick files from the **Google Drive**, **Dropbox**, or **OneDrive** tabs. 3. Wait until each spinner turns into a thumbnail.
Image to Text wizard on Add files, with the project name field, source tabs and an empty drop zone

The three steps run along the top of the card; badges 3 to 6 are the four ways to add pages.

You should see a thumbnail for each page. Files upload as soon as you add them; the eye and bin icons preview or remove a page. Leave now, and the project waits as **Not started** with **Continue setup**.
Two uploaded field-note pages with a files-allowed counter and the Next Step button

Next Step turns blue once every upload has finished.

Click **Next Step**. {% file src="/files/A6a6zLypBGoL1GY7JGqu" %} Sample field notes, page 1 (invented) {% endfile %} {% file src="/files/wSYwwUcy6m23HUN9HhAb" %} Sample field notes, page 2 (invented) {% endfile %} ## Step 2: Pick the language and the kind of material Choose the language of the writing in the **Language** column, then the kind of material in the **Domain** column. The domain adds instructions to the transcription prompt, such as how to treat crossed-out words or the grid of a form. Modern English pages have domains such as **Handwritten Content**, **Forms and Questionnaires**, and **Scanned Documents**; most other languages offer **General**. Not sure of the language? Pick **Auto-detect** at the top of the list. Pick **Custom** in either column to name a language or describe the material yourself.
Language and Domain columns with English and Scanned Documents selected, and the added prompt text below

The box under the columns shows exactly what the chosen domain adds to your prompt.

The bar at the bottom names the **Sample page** the next step will test. Click **Test a different page** to pick another, then click **Next Step**. You should see the review step, usually with the sample transcribed. ## Step 3: Check the free sample, then run every page Evidano transcribes the sample page with the **Transcription prompt** shown at the top. Samples are free, so test as often as you like. Compare the page image with the text beside it, using the zoom icons above the image (**Fit to view** shows the whole page).
Review step showing the prompt, the sample page beside its transcription, and two verdict cards

Read the right-hand text against the image before you choose a verdict card.

Then choose a card: * **Transcription looks good, proceed with this prompt for all N files** runs the same prompt on every page. * **Transcription looks bad** offers **Edit prompt and try again** (change the prompt, then **Transcribe again**) or **Retry with a more advanced AI model**, which reads difficult handwriting better and costs more per page. Approving its result runs it on every page. {% hint style="warning" %} **Costs money:** Pages beyond your free allowance are charged per page from your wallet, at a higher rate for the advanced model. The **Confirm image transcription charge** dialog shows the amount and asks you to confirm first. See [Plans, Limits & Credits](/ailyze-docs/reference/plans-limits-and-credits.md). {% endhint %} ## Step 4: Read, correct, and export the text Your project list opens with a card for every page, which moves from **Queued** to **In progress** to **Completed**; the list updates itself. Open a completed page to see the image beside its transcription, then: * Click **Edit**, correct the text, and **Save**. * Click **Mark verified** once you have checked a page. * Click **Copy**, or download the page as **DOCX** or **XLSX**. **Spreadsheet** in the project header downloads every page in one workbook. ## Next steps * Find themes in the text you produced: upload the DOCX files as described in [Analyze Your First Transcript](/ailyze-docs/getting-started/analyze-your-first-transcript.md). * PDFs, historical handwriting, bulk downloads, and every other option: [Convert Images & PDFs to Text](/ailyze-docs/prepare-research-data/convert-images-and-pdfs-to-text.md). * Unreadable output or a stuck page: [Image to Text Issues](/ailyze-docs/troubleshooting/image-to-text-issues.md).