GitHub

ayutaz / sanoTTS-jp

Real-time synthesis of Japanese TTS with 559 K parameters on ESP32-S3. Morphological analysis and accent estimation of Kanji-Kana mixed text run on the device (confirmed on M5Stack CoreS3 actual machine). Inference is done with dependency-free C99, with a browser demo available. Japanese clean-room reimplementation of sanoTTS from arXiv:2608.21378. ⚠️ The code is MIT, but the weight distribution model is not MIT (LICENSE-MODEL.md. Usage restrictions propagate to the output)

Description in other languages

Statistics

Statistics as of Nov 17, 2026

GitHub stars
71
+3 (Oct 13〜)
Last commit
Nov 2026
Created on GitHub
Aug 27, 2026
Listed
Sep 14, 2026

Stars over time

66687072NovSepJulMayMarJan 202671
Show as a table
MonthStars
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 2026—
May 2026—
Jun 2026—
Jul 2026—
Aug 2026—
Sep 202667
Oct 202670
Nov 202671

Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.

Popular in the same category

Resources in similar research fields

Learn from slides & articles