Model · Voice and speech

Kokoro-82M

A small, free text-to-speech model that reads text aloud in 54 voices across 8 languages. It is light enough to run on modest hardware and may be used commercially. It does not copy voices.

Go to Kokoro-82M’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
Apache-licensed weights; pip package 'kokoro'.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Apache License 2.0 (Permissive (e.g. Apache 2.0, MIT))
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes
Follows from Apache 2.0; card says the model is used in commercial APIs and welcomes real-world deployment.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free to download; a free demo runs on Hugging Face
Plans below.
How you use it: On your own computer, Through another service
Official demo Space on Hugging Face; fal listed as an inference provider. Output is 24 kHz audio.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
Installed with pip and apt; the hosted demo needs no setup.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: hexgrad
Published by the hexgrad account on Hugging Face; architecture based on StyleTTS 2. No company or country stated.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: Available
v1.0 released 27 Jan 2025; earlier v0.19 (Dec 2024) had 1 language and 10 voices.
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A voice or speech, read my text aloud (main use)

text to audio

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Hugging Face, fal

Other options for “A voice or speech, read my text aloud”

Adobe Firefly, Akool, Amazon Polly, Arcads, Async (formerly Podcastle), Azure AI Speech, Bark, CAMB.AI, Cartesia, Chatterbox, Clipchamp, Deepgram, DeeVid AI, Descript, Dia, Dubverse, Eleven v3, ElevenLabs, F5-TTS, fal, Filmora, Fish Audio, FlexClip, Fliki

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.