hjLabs AI Playground
Starting the on-device runtime…
SpeechT5 TTS is a 144M-parameter ONNX model that synthesises speech audio from written text. On this page it runs entirely inside your browser: the 178 MB download comes straight from the Hugging Face repository “Xenova/speecht5_tts” 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.
Runs through plain pipeline() and clones a voice from any x-vector speaker embedding — more robotic than Kokoro but far more hackable. 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 about 8k downloads a month. It is a specialist choice rather than a default, which is exactly why it is worth trying when the popular model gets your particular input wrong.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running SpeechT5 TTS here is the one-off 178 MB download, and once that is cached the page keeps working with the network switched off.
speecht5 ttsspeecht5 tts onnxspeecht5 tts browserrun speecht5 tts locallyxenova/speecht5_ttstext to speech modelspeecht5 tts webgpuspeecht5 tts download sizefree text to speech modeltransformers.js model
About 178 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. Xenova/speecht5_tts 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.