HaruSpeak. Voice-first AI speaking practice for JA / ZH / EN — offline STT, furigana + pinyin, works with any cloud or local LLM (LM Studio, Ollama).

github.com/YANG-Haruka/HaruSpeak

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.