Qwen3-4B with the AI writing tics trained out in one minute
Best for: Local-LLM tinkerers and researchers who want a small model that writes short English prose without common assistant tics.
Biggest catch: The author says the voice is flat, it still invents names and places, and it runs long (~200 words when asked for 150)
Skip it if: You want a hosted writing app, long-form, code or non-English output, or text that passes AI detectors.
Price: Free: open weights under Apache-2.0 on Hugging Face (bf16 merged model, LoRA adapter, Q4_K_M 2.5 GB and Q8_0 GGUF). Runs locally via Ollama, llama.cpp or transformers; no hosted version. (checked Oct 20, 2026)
Full Qwen3-4B with the AI writing tics trained out review
AI Writing Tools · Content Creation
Best for: ML hobbyists and Korean-language enthusiasts curious about handwriting synthesis.
Pros
- A write-up and demo of a neural network that draws Hangul as pen strokes, released for Hangul Day 2026
- Built from ~4,500 lines of real handwriting collected with a smartpen, adapting Alex Graves’ handwriting RNN
- Nice, concrete explainer for anyone curious how stroke-level handwriting generation works
Biggest catch
It is a blog post / research demo, not a product you sign up for
Skip it if: You need a production handwriting or font tool.
Starting price: Free to read; no paid product (checked Oct 14, 2026)
Full Happy Hangul Day! An RNN for Generating Korean Handwriting Strokes review · Happy Hangul Day! An RNN for Generating Korean Handwriting Strokes alternatives
Sources for Happy Hangul Day! An RNN for Generating Korean Handwriting Strokes
AI Writing Tools · Content Creation
Best for: Serious fiction writers.
Pros
- Local-first Mac writing workspace for novels, canon and research
- AI optional
- One-time price
Biggest catch
Mac (Apple Silicon) only
Skip it if: You need cloud collaboration.
Starting price: $30 one-time (beta; launch price $49) (checked Oct 14, 2026)
Full Folian review · Folian alternatives
Sources for Folian
Pros, catches and prices are compiled from public sources (official pricing and docs pages, published reviews, user reports), not hands-on testing. Prices change often, so check the vendor page before you buy.