Models and media
These add-ons are pages for working with models and media. The routes that they call stay in LocalAI.
In the current development builds, this add-on is in the development channel of the add-on library, so it can change. At a glance Topic Detail What it adds A page to make images, video, 3D models, speech, sound and transformed audio with the models you have installed, and to keep what you make. Who installs it An administrator, from Add-ons, Find add-ons, with Install and turn on. With authentication off, you are the administrator. Who turns it on A person needs the addons feature, which is off by default for new users on a server with accounts. The page opens at /app/addons/studio/studio. Note Studio is an add-on. It is not part of the web bundle: install it from Find add-ons in the Add-ons page with Install and turn on. Once it is usable, it is in My add-ons and can be shown in the sidebar, and it opens at /app/addons/studio/studio. Use its canonical add-on page address.
Have a spoken conversation with a model: your voice goes in, the answer is spoken back.
Recognise who is speaking, keep the voices that text to speech can use, and speak text with them.
Find out whose face is in a photo, or whether two photos show the same person.
Train an adapter on your own data, then export it as a model you can chat with.
Shrink a model to a smaller quantized file, then import it so you can chat with it.