About Metadata Studio

Why Metadata Studio exists

Describing a folder of stock images by hand is slow and repetitive: every file needs a tight title, a short description, an ordered keyword list and, for Shutterstock, one or two categories from the official taxonomy. Metadata Studio automates that first pass with a vision model, keeps every field editable, and hands you a CSV the marketplace accepts. It is built for individual photographers, small agencies and sellers who want good metadata without a subscription because of it. See the full feature list or the use cases for where it fits.

Bring your own key, keep your privacy

Metadata Studio is bring-your-own-key. You add an API key from Gemini, OpenRouter or Groq, and it is stored only in your own browser's localStorage. Each request is forwarded through a stateless relay so the provider can be called; the key is never stored on the server, never written to logs, and redacted from error messages. There is no account, no server-side history and no database. Uploads are capped at 25 MB and checked by MIME type and magic bytes, and the app ships a strict Content Security Policy, request validation and rate limiting.

The trade-off is honest: you supply the model access, so provider quotas and billing stay between you and your provider. Clearing your browser storage removes your keys.

Who builds it

Metadata Studio is developed and maintained by Mizanur Rahman Momin. It grows out of practical work on stock and microstock metadata, with guides and tutorials published at mizanursguide.com and tooling from Convo Digital.

Metadata Studio is an independent project. It is not affiliated with, endorsed by or sponsored by Adobe or Shutterstock. Those names describe the CSV formats the tool exports, nothing more. Questions, corrections and feature notes are welcome through the contact page or the FAQ.