Do you know – with calligrapher.ai, you can simulate handwriting with a neural network that runs in a browser via JavaScript. Once you type a sentence, the calligrapher.ai renders it as handwriting in nine different styles, each of which is adjustable with properties such as speed, legibility, and stroke width. It also allows downloading the resulting fake handwriting sample as an SVG image file.
Interestingly calligrapher.ai doesn’t use a font. Typefaces that look like handwriting have been around for many years, but each letter comes out as a duplicate no matter how many times you use it.
Calligrapher.ai “draws” each letter as if it were written by a human hand, guided by statistical weights. It is said that, those weights come from a recurrent neural network (RNN) that has been trained on the IAM On-Line Handwriting Database, which contains samples of handwriting from 200+ individuals digitized from a whiteboard over time. The Calligrapher.ai handwriting synthesis model is therefore primarily geared towards writing in English language.
Since the algorithm producing the handwriting is statistical in nature, its properties, such as “legibility,” can be adjusted dynamically. This might be particularly useful for graphic designers who shall need more customized handwritten scripts than a static font with typefaces.
With neural networks now tackling text, speech, pictures, video, and now handwriting, it seems like no corner of human creative output is beyond the reach of generative AI.
Thanks for Reading. Stay Tuned!
Look forward to connecting with you!
Finally, “subscribe” to my newsletter, so that you get notified every time when I publish.
Check out some of my videos here, and do subscribe to my channel.
Leave a Reply