MiniSpeech

Licenses and credits

MiniSpeech brings together open-source models and libraries. Here is each of them, its license and where to find its source code. The site’s own code is MIT-licensed.

Models

ModelLicenseSourceStatus
Kokoro 82MKokoro-82M by hexgrad (Apache-2.0); ONNX export by onnx-community.Apache-2.0huggingface.co · onnx-community/Kokoro-82M-v1.0-ONNXavailable
Kitten TTS nanoKitten TTS by KittenML (Apache-2.0). The browser runtime embeds eSpeak NG data (GPL-3.0).Apache-2.0github.com · KittenML/kitten-tts-nano-0.8-int8soon
Supertonic 3Supertonic 3 by Supertone Inc. (OpenRAIL-M weights, MIT SDK). Use restrictions of the OpenRAIL-M license apply.OpenRAIL-Mgithub.com · Supertone/supertonic-3soon
Whisper tinyWhisper by OpenAI (MIT); ONNX export by onnx-community.MITgithub.com · onnx-community/whisper-tinysoon
Whisper baseWhisper by OpenAI (MIT); ONNX export by onnx-community.MITgithub.com · onnx-community/whisper-basesoon
Whisper smallWhisper by OpenAI (MIT); ONNX export by onnx-community.MITgithub.com · onnx-community/whisper-smallsoon
Moonshine tinyMoonshine by Useful Sensors (MIT); ONNX export by onnx-community.MITgithub.com · onnx-community/moonshine-tiny-ONNXsoon
Moonshine baseMoonshine by Useful Sensors (MIT); ONNX export by onnx-community.MITgithub.com · onnx-community/moonshine-base-ONNXsoon

Software

ComponentVersionLicenseUsed forSource
eSpeak NGphonemizer.js 1.2.1GPL-3.0-or-laterphonemization (English)espeak-ng/espeak-ng
phonemizer.js1.2.1Apache-2.0phonemization (English)xenova/phonemizer.js
kokoro.jsmain, 2026-11-07Apache-2.0text splitting and normalizationhexgrad/kokoro/tree/main/kokoro.js
Transformers.js4.3.2Apache-2.0running the modelshuggingface/transformers.js
ONNX Runtime Web1.31.0-dev.20260914-8d85527a0MITrunning the modelsmicrosoft/onnxruntime
Astro7.4.7MITthe sitewithastro/astro
Bricolage Grotesque5.3.0OFL-1.1fontsateliertriay/bricolage
Hanken Grotesk5.3.0OFL-1.1fontsmarcologous/hanken-grotesk
MiniSpeechMITthe site

eSpeak NG is GPL-3.0. It runs as a separate program (a Web Worker) that receives text and returns phonemes; that file is served as is, unminified: /workers/phonemizer-espeak.js. The GPL does not cover the audio you create: your files are yours.