hjLabs AI Playground
Starting the on-device runtime…
Kokoro 82M v0.19 is an 82M-parameter ONNX model that synthesises speech audio from written text. On this page it runs entirely inside your browser: the 92 MB download comes straight from the Hugging Face repository “onnx-community/Kokoro-82M-ONNX” into your browser cache, and every inference after that executes on your own GPU through WebGPU. That is a one-off download of well under a minute on a normal connection, and small enough that integrated graphics handle it without complaint. It is an English-language model; expect quality to fall off sharply on other languages.
The original Kokoro release. Same kokoro-js path as v1.0; keep it only if you prefer the older voice set. In practice people reach for a model like this for voicing drafts, generating narration, and accessibility read-back — with no per-character billing.
Available precisions: q8 (8-bit) and fp32 (full precision). q8 comes first because it roughly halves the download at a quality cost you will struggle to measure on this class of model; fp32 is there when you want the reference numbers. Hugging Face records around 51k downloads a month — steady, real usage rather than a one-off research drop.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running Kokoro 82M v0.19 here is the one-off 92 MB download, and once that is cached the page keeps working with the network switched off.
kokoro 82m v0.19kokoro 82m v0.19 onnxkokoro 82m v0.19 browserrun kokoro 82m v0.19 locallyonnx-community/kokoro-82m-onnxtext to speech modelkokoro 82m v0.19 webgpukokoro 82m v0.19 download sizefree text to speech modeltransformers.js model
About 92 MB for the q8 build, including the tokenizer and config files the runtime also has to fetch — this is the whole payload, not just the weights file. It is downloaded once and then served from the browser Cache Storage API.
Yes, through the WebAssembly fallback, which is slower but works anywhere. WebGPU (Chrome or Edge 113+, Safari 26+) is what makes it feel interactive. On WASM, prefer the smaller quantized build.
No. onnx-community/Kokoro-82M-ONNX is a public repository, so your browser fetches the ONNX files directly over HTTPS. There is no account, no key and no server in between.
No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.