Nano-Edge-TTS
A 1.75M-parameter decoder for Kokoro-82M that runs no neural network at audio rate.
Nano-Edge-TTS launched on 15 November 2026. It ranked #113 on Daily Launch on 16 November 2026 with a Launch Score of 10, from 13 points on Show HN. It was new in the ranking that day.
What is Nano Edge TTS?
A 1.75M-parameter decoder for Kokoro-82M that runs no neural network at audio rate. Kokoro's text side (pronunciation, timing, pitch and all voices) is unchanged. Its 53.3M-parameter waveform decoder is replaced by two small networks that run 80 and 160 times a second and set per-frequency gains on a pulse train and on white noise. Two inverse STFTs turn the result into audio.
From its model card on Hugging Face
Nano Edge TTS (Nano-Edge-TTS) is a launch on Show HN. It is released under the Apache 2.0 license.
How to get Nano Edge TTS
pip install kokoro==0.9.4 safetensors soundfileFrom its model card on Hugging Face
In its own words
70x realtime, Lightweight Kokoro-based TTS model
From its Show HN post
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 10 of 100 on 16 November.