Models Model details

Hexgrad

hexgrad: Kokoro 82M

hexgrad/kokoro-82m

Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese) using 54 preset voices organized by language and gender. At 82M parameters, it is well-suited for multilingual TTS deployments where footprint and cost efficiency matter.

Input
$0.62

/ 1M tokens · Token reference

Output
$0

/ 1M tokens · Token reference

Context window
4.1K

tokens

Speech output · Token reference fields do not establish an output-unit price.

Limits

Context

4,096

tokens

Max output

3,686

90% of the context window

Model facts

Author

Hexgrad

Tokenizer

Other

Modality

Text -> Speech

Created

Apr 23, 2026

Publication status

Hugging Face: not mappedLicense: not publishedParameter count: not published

Modalities

Input · TextOutput · Speech