tiny-voca
Tiny-voca is a 4.5M-parameter English text-to-speech model. This page runs it in your browser.
tiny-voca launched on 14 November 2026. It ranked #104 on Daily Launch on 19 November 2026 with a Launch Score of 15, from +49 stars on 19 Nov on GitHub. It moved down 68 places from the day before.
What is Tiny Voca?
tiny-voca is a small English text-to-speech model. It has two voices, 4.5M parameters, and runs on a CPU or in the browser. Long text is fine. It is read one sentence at a time and the audio is joined. A text that ends without a mark gets a full stop, so the last word does not break off. A sentence with nothing to read, such as one in another script, is skipped. The output never peaks above 0.99, so it does not clip as a 16-bit WAV.
From its README on GitHub
Tiny Voca (tiny-voca) is a repo by n4ze3m on GitHub. It is written in Python and released under the Apache-2.0 license.
How to get Tiny Voca
Get it from its repository on GitHub.
In its own words
A 4.5M-parameter two-voice English text-to-speech model, trained from scratch
From its GitHub repository
Launch timeline
Launch Score, last 7 days
#76 of 226 in the roundup for the week of 16-22 November 2026.