I was frustated by having to draw system design diagrams by hand when discussing it with my team mates or in an interview. So I thought "Wouldn't it be great if someone draws it for me, while I think out loud?".
That is when I came up with VoiceDraw. You can just think out loud or discuss your system architecture with a friend/interviewer, the diagrams are automatically drawn along with your reasoning, open questions and tradeoffs beautifully written on to the side.
As a blind software developer this looks interesting, but the output descriptions are not useful. I asked it "create a diagram for a rest api with a database, app server, and cache." The diagrams alt text was "609 / 100k tokens used" The text it returned was "Created a simple REST API architecture with three core components: a web app server, a cache layer, and a database. Organized them into logical tiers." If it can generate the diagram it would be nice if the alt text was a detailed description of the diagram.
Great point, I hadn't considered this use case. I've added richer, screen-reader-friendly diagram descriptions to the roadmap. Thanks for the feedback!
Would be curious to connect and compare notes! Yours is probably way better, I had built mine as a prototype and specifically interested in running all models local and in browser.
Cool to see that you did transcription AND LLM for the diagram with "in-browser" / local.
Tangent: But I'm wondering whether there would be something from the browser side to enforce this?
Like a sandbox so that my browser allows me to launch this via "download" only so that after I download everything there is no way for the website to get any of my data.
As a (non-technical) user what kind of guarantee do I have that the prompts, transcript etc. are treated only local?
It's a great idea and something I would absolutely use. However I can't get it to draw anything at all. I just get one single box or some messy rubbish
Thanks for reporting. Could you share your browser, OS, and country? Also, did voicedraw.com fail to load entirely in the browser, or were you able to open the site before seeing the error?