Launched this week
BUD
Voice-first canvas for sketchnoting and whiteboarding
124 followers
Voice-first canvas for sketchnoting and whiteboarding
124 followers
Ideate, sketch, and edit diagrams in real time on a voice-first canvas. Speak naturally to build system architectures, flowcharts, and turn ideas into visuals.
BUD
The .excalidraw export is the detail that sells it for me — means the output stays real editable elements, not a flattened image I'd have to redraw. Once I export a diagram and tidy it up by hand in Excalidraw, can I bring that file back into BUD and keep refining it by voice, or is the voice editing one-way out? Trying to figure out if BUD is the whole loop for me or just the fast first-draft step.
BUD
Good to know it's both ways for now — that flexibility is what makes it usable. On the Excalidraw round-trip specifically: if I edit the exported .excalidraw and upload it back, does BUD preserve its own structure/linking so it stays editable in the canvas, or does re-importing flatten it into a static drawing I can't keep iterating on inside BUD? That reimport fidelity is really what decides whether it's a full loop or a one-way handoff for me.
BUD
@leo404 Yep! BUD preserves the structure, and it stays editable. It never becomes a static/flattened image in BUD, you can always edit it out and keep iterating as you want.
Would love to see an export option to PDF or PNG once the diagram is done, sometimes I need to drop the visual into a slide or doc without recreating it. Could make the handoff from voice-to-visual way smoother.
BUD
@ferhat160021 Thanks for the feedback. Actually you can export it as a png or .excalidraw file for now just by instructing BUD to export it for you. But pdf export will be added soon.
A voice-first canvas for diagrams sounds genuinely fresh. One thing that would make it click for me is the ability to undo or branch a conversation, so if I misspoke mid-flow the diagram doesn't get wrecked and I can try a different phrasing without starting over.
BUD
@ceylangrrjlhl Thanks for flagging that up. Will add this functionality in the next version.
Spoke out a quick system design and watched it appear as a clean diagram, which felt kind of magical for someone who hates dragging boxes around. Curious how it handles more complex edits though.
BUD
The voice-first canvas concept is genuinely refreshing for diagramming, which has felt stale for years. Excited to see how the natural language parsing handles ambiguous ideas like "make it connect better" or "show the flow back to auth."
BUD
@miranpq1 Thanks! Hope you like it.
Voice-first for diagramming is an interesting bet — most whiteboard tools still assume you're reaching for a mouse first. The real test will be accuracy on technical vocabulary (service names, arrows/relationships) since that's where voice-to-diagram tools usually fall apart on system architecture use cases specifically.
BUD
@cosmicbunny Yep! We've kept the technical vocabulary in our mind while building BUD. Do give it a try.