Model reference · open weights

Kokoro-ONNX

Kokoro-ONNX is an open-weight audio or speech model from onnx-community, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio onnx-community 1 variants 1.1M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Kokoro-ONNX is

Kokoro TTS Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). Table of contents - Usage - JavaScript - Python - Voices/Samples - Quantizations Usage JavaScript First, install the kokoro-js library from NPM using: You can then generate speech as follows: Python Optionally, save the audio to a file: Voices/Samples Life is like a box of chocolates. You never know what you're gonna get. Quantizations The model is resilient to quantization, enabling efficient high-quality speech synthesis at a fraction of the original model size. How could I know? It's an unanswerable question. Like asking an unborn child if they'll lead a good life. They haven't even been born.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makeronnx-community
TypeAudio & music
Variants1
Runs withtransformers.js
Based onhexgrad/Kokoro-82M
Released2025-02-07
Popularity1.1M downloads / month
Likes253
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Kokoro-82M-v1.0-ONNXBF16Weights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys kokoro-onnx for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kokoro-onnx below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="kokoro-onnx" -F file=@audio.mp3

Details

Languages, data & research

Languages

en

Tags

transformers.js onnx style_text_to_speech_2 text-to-speech en

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Kokoro-ONNX on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms