Automatic Speak2Print via ComfyUI , TripoSR, and Prusaslicer
11Automatic printing of a 3d model from a single voice command
How It Works
-The system first captures the name of the desired item through JavaScript's recogniseSpeech function.
-It then incorporates this name into a JSON workflow and transmits it to ComfyUI to produce an image based on the provided prompt.
-ComfyUI generates a 3D model from the image, which is displayed on the device and passed to the next script.
-The model is then processed by Prusaslicer to adjust parameters like rotation and size, and to generate the G-code.
-Finally, the G-code is uploaded to the printer (Octoprint) using an API key.
Github is at https://github.com/diggedypomme/Print...
This is probably of very little useable value, but I've had my fun, and that's all that matters