avsync-live / harmony Goto Github PK

To reduce unnecessary API requests if they are not necessary

For example, goals come after cognition

Perhaps Capabilities isn't really needed?

This would make document editing and file sharing easier

This will allow for creating, storing, and relating Projects, Entities, Roles, etc.

Strapi will provide user accounts, permissions, and much more. A lot of the code already exists for AVsync.

Lexi can learn the API and use it to ask for information. For example, when the user asks for information about upcoming events, tasks, projects etc, Lexi could be trained to recognize what the user is asking for, and provide a response that triggers a request to the API. The response from the API would then be provided to Lexi, who would then format and interpret the results for the user.

It could also possibly replace markdown files as the way data scripts and documentation are stored, although that has potential drawbacks when it comes to simplicity.

You should be able to end Lexi's speech if desired. Currently, that's not possible.

Lexi.studio could possibly run a system with NAS capabilities to store files, using Nextcloud for documents, video, chat, and more, and nginx to reverse proxy to your personal brand and host your personal website.

A guide would have to be created to change your home's firewall.

https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-synthesis-markup

Photopea is a great web based tool for photo editing that would be very useful along side AVsync and Invoke AI.

https://replicate.com/collections/image-to-text

Upload a PDF or image to get the text

Pretty sure that's what's happening

Parentheses make it fail.

Similar to "Add to Playlist" on YouTube using Modal, has default automatic choice.

"I'm sending you the first of two pieces of a longer text"