AI Visual Tagging
CodeConda LLC · Image · Video
PhotoTag.ai is an AI visual tagging tool that writes keywords, titles, and descriptions for photos and videos, then exports them as IPTC, XMP, EXIF, or CSV metadata.
About AI Visual Tagging
What Is PhotoTag.ai
PhotoTag.ai is a browser-based keywording service from CodeConda LLC. You upload a photo or video, the model reads the scene, and it returns a title, a description, and a set of keywords you can edit before export. Most people find it through a search for a photo keyword generator, then stay for the batch queue.
The tool sits in front of the upload step instead of replacing your catalog. It writes image metadata into the file or hands you a CSV that stock platforms accept, so Shutterstock, Adobe Stock, Freepik, and similar sites get the same terms your editor approved. A Lightroom Classic plug-in covers desktop work, and an API covers automated pipelines.
The limits matter here. Every file costs one upload credit, videos included, and there's no subscription tier with unlimited runs. New accounts get 3 free credits. Niche subjects still need a human pass, because a model can misread a prop, a location, or a mood.
Getting Started
- Create an account at keyword.camera, which redirects to phototag.ai, and confirm your email.
- Buy a credit pack or start with the 3 free uploads.
- Upload a batch, then set the language, title length, and any custom instructions in the upload settings.
- Review the generated keywords and descriptions, drop weak terms, and export with embedded metadata or as a CSV file.
Product Information
A quick look at AI Visual Tagging's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Microstock contributors
- E-commerce sellers
- Marketing teams with a shared asset library
Tasks
- Bulk keywording a new shoot
- Video tagging
- Metadata cleanup on an old catalog
Scenarios
- A weekend shoot before a Monday upload window
- A product catalog refresh with hundreds of SKUs
- Localized listings for non-English marketplaces
Key features
Batch Queue for Large Uploads
The uploader accepts up to 1,500 files at once on the largest pack, 1,000 on the mid pack, and 500 on the entry pack. Each file returns a title, a description, and a keyword set, and you can edit any result before export. The queue is what separates this from typing tags one image at a time.
Titles and Descriptions in One Pass
PhotoTag.ai generates all three metadata fields together, so the title, description, and keywords describe the same scene instead of drifting apart. You can cap the title or description length in the settings, which helps when a marketplace enforces a character limit.
Metadata Export and CSV for Stock Sites
Results can be written into IPTC, XMP, EXIF, or QuickTime metadata inside PNG, JPEG, WEBP, TIFF, MP4, and MOV files. The CSV route covers more than 20 stock platforms, including Shutterstock, Adobe Stock, iStock, Dreamstime, Freepik, Pond5, and Motion Array. Both paths keep bulk keywording out of a spreadsheet.
Lightroom Classic Plug-in
The plug-in pulls selected photos from a Lightroom Classic catalog, sends them for tagging, and writes the results back. Photographers who already cull and edit in Lightroom don't have to export files to a folder first. It's a desktop-only add-on, so mobile workflows are out.
Keyword API for Automated Pipelines
The API accepts a file and returns titles, descriptions, and keywords for developers who run their own intake tools. Teams that process client uploads can call it from a script instead of asking someone to drag files into the web app. Access comes with an account and credits, not a separate contract.
Tagging in More Than 15 Languages
Images and videos can be tagged in Spanish, French, German, Portuguese, Italian, Japanese, Korean, Chinese, Arabic, Hindi, and several others. That covers localized marketplace listings and regional catalogs without a second tool.
Context From Existing Metadata and Custom Instructions
You can tell the model to read the file's current metadata for context, or add your own instructions about tone, naming, or preferred terms. This is the setting that keeps a brand from getting generic tags like "business" on every shot.
Pros and cons
Pros
- Credits are bought once and never expire, so a slow month doesn't burn a subscription.
- Per-file cost falls from about $0.009 on the entry pack to about $0.0038 on the 50,000 pack.
- Handles stills, vector SVG, and video in one queue, which few keywording tools do.
- CSV export maps to more than 20 stock platforms, plus embedded IPTC metadata for direct uploads.
- Custom instructions and existing metadata give you control over tone and terminology.
Cons
- There's no unlimited plan, so heavy users keep buying packs and can't forecast a fixed monthly cost.
- The free allowance is 3 files, enough to test the output but not to judge a full shoot.
- Results on niche subjects still need a review pass, and that time grows with batch size.
- Batch size and file size caps depend on the pack you bought, which feels arbitrary when a 100MB TIFF fails on a small pack.
Frequently asked questions
It reads an image or video and writes a title, a description, and a list of keywords for it. You can export those fields as embedded metadata or as a CSV for stock platforms.
Related content
Explore related tools, skills, and articles for AI Visual Tagging.
AI Visual Tagging Alternatives
Google EmbeddingGemma 2
Google DeepMind · Writing · Image · CodingGoogle EmbeddingGemma 2 is a 740M-parameter open model that turns text, code, images, audio, and video frames into vectors in one 768-dimension space, running on phones and laptops.
Tractionwave
TractionWave · Image · MarketingTractionWave is an AI attention heatmap tool for static ads. Upload a PNG or JPG and it returns predicted attention, ranked hotspots, and fixes before you spend budget.
Imejis.io
Imejis.io · Image · MarketingImejis.io is an AI design studio for agents and marketing teams. Describe an image in plain words, and it writes the copy, builds the layout, reflows it to every size, then exports a finished file.