lokutor-ai /
ito
Natural-sounding streaming text-to-speech for the ESP32-S3: 4.4 M params, 4.9 MB, no cloud, no NPU
Updated 35 min ago
+2 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It is English-only and needs a host computer running espeak-ng to convert text to phoneme ids before sending them to the chip over serial. The default build uses the row split for stable power.
Summary written by AI from the repository’s description and README.
lokutor-ai / ito
View on GitHub(opens in new tab)