@berryxia: Guys, I did it. Just using Opus 4.8, about two rounds of conversation to achieve this effect — you can draw CAD by voice. For example: draw me a sphere, circles, etc. Basic demos work fine, but for industrial use, there's still a gap. However, for making demos, I think it's totally okay...
Summary
The user demonstrated a basic demo of generating CAD graphics via voice using Opus 4.8 with just two rounds of conversation, noting it's not yet industrial-grade but suitable for demos.
View Cached Full Text
Cached at: 05/29/26, 12:06 PM
Hey guys, I did it.
Just using Opus 4.8, it takes about two conversation turns to get this effect — you can draw CAD with natural language.
For example: draw a sphere, a circle, anything like that.
Basic demos definitely work, but there’s still a gap before it’s ready for industrial use.
But for making demo presentations, I think it’s totally fine. Go check it out. https://t.co/P7ICLzDNFS
Berryxia.AI (@berryxia): Everyone’s getting more impressive by the day! Coding software used to be enough to satisfy everyone, but now people are moving to natural language → 3D CAD for coding.
Similar Articles
@0xQiYan: Still drawing architecture diagrams manually? Dragging and tweaking for half a day? Bookmark this! Today I have to recommend this skill—I recently installed `drawio-skill`, and with just one sentence it can generate professional diagrams, no more drawing by hand. The logic is very simple: just speak naturally (e.g., "draw a trading system architecture diagram"), and it generates the diagram directly...
Introducing the drawio-skill tool, which generates professional diagrams such as architecture diagrams, flowcharts, ER diagrams, etc., based on natural language descriptions. It supports multi-round iteration and export to various formats, significantly improving diagramming efficiency.
@shao__meng: Last night I used Cursor (Opus 4.7) + Remotion to make a video. After the first version was complete, there were quite a few issues—font and background color blending, text overlapping, etc. I was a bit harsh with my words, something like: 'Terrible, so many issues, didn't you check before outputting?' and pointed out a few specific problems. …
The article shares a personal experience using Cursor and Opus 4.7 to generate videos, highlighting the agent's rigorous self-correction process. It then transitions into a technical discussion on 'Agent = Model + Harness,' arguing that engineering systems like ratchets and context management are more critical to AI agent performance than the underlying model alone.
@QingQ77: Open-source framework enables Codex, Claude Code and other coding agents to generate CAD models from text descriptions, export to STEP/STL/3MF and more. https://github.com/earthtojake/text-to-cad… text-to-…
The open-source framework text-to-cad enables Codex, Claude Code and other coding agents to generate CAD models from text descriptions, supporting export to STEP, STL, 3MF, DXF, GLB, URDF and more. It comes with three built-in Skills (CAD, URDF, and Robot Motion) and runs locally without requiring a backend.
@XAMTO_AI: Can generate architecture diagrams just by speaking? This tool is actually pretty impressive. Speak plain language to Claude, and it directly outputs architecture diagrams, flowcharts, sequence diagrams, data flow diagrams... It also supports one-click switching between dark and light themes, export in multiple formats, all in a single HTML file. Programmers who can't draw are saved, and programmers who don't want to draw are saved too...
Archify is a Claude Skill that allows users to generate architecture diagrams, flowcharts, sequence diagrams, etc. using natural language descriptions, and supports dark/light theme switching and multi-format export.
@GitTrend0x: Blender 里直接喊话生成 3D 模型 https://github.com/Adam-CAD/CADAM 这就是 CADAM，把 ChatGPT / Claude / Gemini 直接变成 Blender 内置 CAD 智能助手的…
CADAM 是一个开源工具，通过自然语言在 Blender 中利用 ChatGPT、Claude 或 Gemini 生成 3D CAD 模型，支持参数化控制和多种导出格式。