DescribeThat

Turn photos and PDFs into structured data using your own Claude key

Intermediate
Screenshot of DescribeThat, Turn photos and PDFs into structured data using your own Claude key

What is DescribeThat?

DescribeThat is a productivity tool that turns photos and PDFs into structured data using your own Claude key. DescribeThat is a free web tool that extracts structured details from photos and PDFs, including people, objects, vehicles, text and scenes. It runs on Claude Sonnet 5 through the user's own Anthropic API key, stored only in the browser.

DescribeThat is a free extraction tool from Iacoletti Software that reads photos and PDFs and returns structured information about what they contain. According to its listing, the output covers people, objects, vehicles, text and finer scene details, so a single upload can produce a broad inventory of everything visible or written in a file. The version shown on the homepage is 5.2, and the engine behind it is Anthropic's Claude Sonnet 5. The tool runs on a bring-your-own-key model. On opening the app, a visitor is asked to paste a Claude API key, which can be created for free in the Anthropic Console. The key is saved locally in the browser and, as the page states, does not leave the device. Before the interface unlocks, the key is verified with Anthropic. Until that step is completed the app shows a "System Restricted" notice and keeps the extraction engine switched off. Help, license and privacy links sit beneath the key form. In practice this suits people who need to turn unstructured visual material into organized notes: researchers cataloguing images, analysts reviewing scanned documents, investigators or administrators who want a detailed written breakdown of a photograph, or anyone who wants text pulled out of a PDF alongside a description of its visual content. The homepage does not describe export formats, batch limits or output schemas, so those details would need to be checked inside the app. Among alternatives, DescribeThat sits between general chat assistants that accept image uploads and dedicated document OCR or data capture platforms. It is narrower than a full document automation suite and has no visible integrations, but it removes subscription cost from the tool itself. The cost that remains is the usage billed by Anthropic against the user's own key, which makes it a lightweight, transparent option for occasional or technical users comfortable managing an API credential.

How do you use DescribeThat?

  1. 1Create an Anthropic API key
    Open the Anthropic Console key settings page linked from the app and generate a free API key. Copy it so it can be pasted into DescribeThat.
  2. 2Open DescribeThat
    Visit the DescribeThat homepage. The app first shows a Configure API Key panel and a System Restricted notice until a key is active.
  3. 3Save and activate the key
    Paste the key and choose Save & Activate. The key is checked with Anthropic and stored only in the browser before the app unlocks.
  4. 4Add a photo or PDF
    Once unlocked, provide the image or PDF to analyze. The extraction engine then reads the file for people, objects, vehicles, text and scene details.
  5. 5Review the structured output
    Read through the extracted results and check them against the original file. Consult the Help link if any behavior is unclear.

Pros and cons

Pros

  • Free to use, with no subscription charged by the tool itselfAI
  • Covers a wide range of detail: people, objects, vehicles, text and scene elementsAI
  • Accepts both photos and PDFs in one toolAI
  • API key stays in the browser and is verified with Anthropic before unlockingAI
  • Built on Claude Sonnet 5, a capable vision-language modelAI

Cons

  • Requires an Anthropic API key, which adds setup friction for non-technical usersAI
  • Usage costs are billed by Anthropic to the user's own account, so volume is not truly freeAI
  • Homepage gives no details on export formats, batch processing or output schemaAI
  • No listed integrations or API for connecting results to other softwareAI
  • Nothing works until a key is added, so the tool cannot be tried without an accountAI

How much does DescribeThat cost?

Pricing

The tool is described as free. Usage runs through the visitor's own Anthropic API key, so any model charges are billed by Anthropic. The homepage does not list paid plans.

Learn more

Support

The homepage links to Help, License and Privacy pages. No contact channels or response times are stated.

Integrations

Connects to Anthropic through a user-supplied Claude API key. No other integrations are listed on the homepage.

Features

Extracts structured information from photos and PDFs, covering people, objects, vehicles, text and scene details. Powered by Claude Sonnet 5, with local browser storage of the API key and key verification before the app unlocks.

Frequently asked questions about DescribeThat

  • How much does DescribeThat cost?
    The tool is described as free. Usage runs through the visitor's own Anthropic API key, so any model charges are billed by Anthropic. The homepage does not list paid plans.
  • How do you use DescribeThat?
    The walkthrough on this page covers 5 steps: 1. Create an Anthropic API key 2. Open DescribeThat 3. Save and activate the key 4. Add a photo or PDF 5. Review the structured output.
  • What platforms does DescribeThat support?
    DescribeThat is available on Web App.
  • What does DescribeThat integrate with?
    Connects to Anthropic through a user-supplied Claude API key. No other integrations are listed on the homepage.
  • What are the limitations of DescribeThat?
    Requires an Anthropic API key, which adds setup friction for non-technical users. Usage costs are billed by Anthropic to the user's own account, so volume is not truly free. Homepage gives no details on export formats, batch processing or output schema.

Status

StatusActive
Views0
Outbound clicks0
Added10/8/2026

Platforms

Web App

Pricing

Free