allalt
allalt, a.k.a, "all images deserve an alt tag", is a simple
CLI tool that transforms images into words. Designed to provide
text-based descriptions of images for visually impaired users, it
leverages the power of
GPT-4V to make visual
content accessible in a textual format.
allalt serves as a handy utility for web developers and content
creators to generate alt text for images, enhancing web accessibility.
The tool is built to be as user-friendly as possible, with a focus on ease of use and accessibility.
Installation
From source
First install the dependencies:
- Go 1.21 or above.
- make.
- scdoc.
Switch to the latest stable tag, v0.2.0, then compile and install:
git checkout v0.2.0
make
sudo make installUsage
$ allalt --help
NAME:
allalt - describe images for visually impaired users
USAGE:
allalt [global options] [arguments...]
VERSION:
0.1.0
GLOBAL OPTIONS:
--key value, -k value the OpenAI API key to use [$ALLALT_KEY]
--language value, -l value the language to use when describing images (default: "en_US") [$ALLALT_LANGUAGE]
--context value, -c value the context around the image to use when describing images [$ALLALT_CONTEXT]
--keyword value, -K value [ --keyword value, -K value ] potential keywords relevant to the image
--help, -h show help
--version, -v print the versionSee allalt(1) after installing for more information.
Contributing
Anyone can help make allalt better. Send patches on the mailing
list and report bugs
on the issue tracker.
You must sign-off your work using git commit --signoff. Follow the
Linux kernel developer's certificate of
origin
for more details.
All contributions are made under the GPL-2.0 license.
Resources
The following resources are available:
- Support and general discussions.
- Patches and development related questions.
- Instructions on how to prepare patches.
- Feature requests and bug reports.
Released under the GPL-2.0 license.